Hugging Face's logo

mlx-community
/
Mage-VL-OptiQ-4bit

Image-Text-to-Text
MLX
Safetensors
mage_vl
optiq
quantized
4bit
mixed-precision
mage-vl
multimodal
vision-language-model
video-understanding
apple-silicon
conversational
4-bit precision
Model card Files
xet
 Community
codelion commited on
Commit
94948e9
·
verified ·
1 Parent(s): 9acaa7c

OptiQ 4-bit quant of Mage-VL (first video family): mixed 4/8-bit Qwen3-4B LM + bf16 Mage-ViT vision sidecar

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. README.md +82 -0
  3. chat_template.jinja +7 -0
  4. config.json +2158 -0
  5. generation_config.json +6 -0
  6. model.safetensors +3 -0
  7. model.safetensors.index.json +1212 -0
  8. optiq/optiq_vision.safetensors +3 -0
  9. optiq_metadata.json +1024 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +21 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: mlx
4
+ pipeline_tag: image-text-to-text
5
+ base_model: microsoft/Mage-VL
6
+ tags:
7
+ - mlx
8
+ - optiq
9
+ - quantized
10
+ - 4bit
11
+ - mixed-precision
12
+ - mage-vl
13
+ - multimodal
14
+ - vision-language-model
15
+ - video-understanding
16
+ - image-text-to-text
17
+ - apple-silicon
18
+ ---
19
+
20
+ # mlx-community/Mage-VL-OptiQ-4bit
21
+
22
+ > **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. [All OptiQ quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)
23
+
24
+ **Video and image understanding, running locally on a Mac.** This is an OptiQ mixed-precision quant of [microsoft/Mage-VL](https://huggingface.co/microsoft/Mage-VL), a 5B vision-language model that reads images and video. It is the first video model in the OptiQ lineup, and it runs entirely on Apple Silicon with no PyTorch. 3.7 GB on disk.
25
+
26
+ Mage-VL pairs a from-scratch Mage-ViT visual encoder with a Qwen3-4B language model. OptiQ quantizes the language tower to mixed 4/8-bit and keeps the vision tower at bf16 in a sidecar, so the same checkpoint does text, image, and video.
27
+
28
+ ## It works on image and video
29
+
30
+ Both of these ran through the quantized model on Apple Silicon, MLX only:
31
+
32
+ **Image** (`examples/dog.jpg`):
33
+ > A dog is sitting on a rug in front of a patterned rug.
34
+
35
+ **Video** (frames sampled from `examples/soccer-broadcast.mp4`):
36
+ > A man is reporting on a soccer game.
37
+
38
+ ## What it is
39
+
40
+ | Property | Value |
41
+ |---|---|
42
+ | Base | microsoft/Mage-VL (Mage-ViT vision + Qwen3-4B, ~5B params) |
43
+ | Method | OptiQ mixed-precision, sensitivity-driven (bf16 reference) |
44
+ | Language tower | per-layer 4/8-bit: 164 layers at 4-bit, 90 at 8-bit |
45
+ | Achieved bits-per-weight | 5.90 |
46
+ | Vision tower | bf16, kept in `optiq/optiq_vision.safetensors` (297 tensors) |
47
+ | On disk | 3.7 GB (3.0 GB language + 0.63 GB vision) |
48
+ | Video | frame sampling (uniform frames), no neural codec required |
49
+
50
+ The vision tower was reimplemented in MLX and validated bit-exact against the reference (max abs diff 1.7e-3 in float32). Following `llama.cpp`'s naming for mixed quants, the "4bit" label denotes the family, not the weighted average.
51
+
52
+ ## Run it
53
+
54
+ Mage-VL ships under an architecture stock mlx-lm does not know, so `import optiq` registers it, and OptiQ loads the vision sidecar:
55
+
56
+ ```bash
57
+ pip install "mlx-optiq>=0.4.7"
58
+ ```
59
+
60
+ For image and video input, serve it with an OpenAI + Anthropic-compatible endpoint:
61
+
62
+ ```bash
63
+ optiq serve --model mlx-community/Mage-VL-OptiQ-4bit
64
+ ```
65
+
66
+ Then send an image (or sampled video frames) as `image_url` content. Text-only generation also loads directly:
67
+
68
+ ```python
69
+ import optiq # registers the mage_vl arch + vision sidecar
70
+ from mlx_lm import load, generate
71
+
72
+ model, tok = load("mlx-community/Mage-VL-OptiQ-4bit")
73
+ print(generate(model, tok, prompt="Hello", max_tokens=100))
74
+ ```
75
+
76
+ Video is handled as sampled frames (the DCVC neural codec in the base repo is an optional efficiency path and is not needed here).
77
+
78
+ ## Links
79
+
80
+ - **Project website:** [mlx-optiq.com](https://mlx-optiq.com/)
81
+ - **All OptiQ quants:** [mlx-optiq.com/models](https://mlx-optiq.com/models)
82
+ - **Base model:** [microsoft/Mage-VL](https://huggingface.co/microsoft/Mage-VL)
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
config.json ADDED
@@ -0,0 +1,2158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MageVLForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 151643,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "image_token_id": 151655,
9
+ "model_type": "mage_vl",
10
+ "quantization": {
11
+ "group_size": 64,
12
+ "bits": 4,
13
+ "mode": "affine",
14
+ "model.embed_tokens": {
15
+ "bits": 8,
16
+ "group_size": 64
17
+ },
18
+ "model.layers.0.self_attn.q_proj": {
19
+ "bits": 4,
20
+ "group_size": 64
21
+ },
22
+ "model.layers.0.self_attn.k_proj": {
23
+ "bits": 4,
24
+ "group_size": 64
25
+ },
26
+ "model.layers.0.self_attn.v_proj": {
27
+ "bits": 8,
28
+ "group_size": 64
29
+ },
30
+ "model.layers.0.self_attn.o_proj": {
31
+ "bits": 8,
32
+ "group_size": 64
33
+ },
34
+ "model.layers.0.mlp.gate_proj": {
35
+ "bits": 4,
36
+ "group_size": 64
37
+ },
38
+ "model.layers.0.mlp.down_proj": {
39
+ "bits": 8,
40
+ "group_size": 64
41
+ },
42
+ "model.layers.0.mlp.up_proj": {
43
+ "bits": 4,
44
+ "group_size": 64
45
+ },
46
+ "model.layers.1.self_attn.q_proj": {
47
+ "bits": 4,
48
+ "group_size": 64
49
+ },
50
+ "model.layers.1.self_attn.k_proj": {
51
+ "bits": 4,
52
+ "group_size": 64
53
+ },
54
+ "model.layers.1.self_attn.v_proj": {
55
+ "bits": 8,
56
+ "group_size": 64
57
+ },
58
+ "model.layers.1.self_attn.o_proj": {
59
+ "bits": 8,
60
+ "group_size": 64
61
+ },
62
+ "model.layers.1.mlp.gate_proj": {
63
+ "bits": 4,
64
+ "group_size": 64
65
+ },
66
+ "model.layers.1.mlp.down_proj": {
67
+ "bits": 4,
68
+ "group_size": 64
69
+ },
70
+ "model.layers.1.mlp.up_proj": {
71
+ "bits": 4,
72
+ "group_size": 64
73
+ },
74
+ "model.layers.2.self_attn.q_proj": {
75
+ "bits": 8,
76
+ "group_size": 64
77
+ },
78
+ "model.layers.2.self_attn.k_proj": {
79
+ "bits": 4,
80
+ "group_size": 64
81
+ },
82
+ "model.layers.2.self_attn.v_proj": {
83
+ "bits": 8,
84
+ "group_size": 64
85
+ },
86
+ "model.layers.2.self_attn.o_proj": {
87
+ "bits": 4,
88
+ "group_size": 64
89
+ },
90
+ "model.layers.2.mlp.gate_proj": {
91
+ "bits": 4,
92
+ "group_size": 64
93
+ },
94
+ "model.layers.2.mlp.down_proj": {
95
+ "bits": 4,
96
+ "group_size": 64
97
+ },
98
+ "model.layers.2.mlp.up_proj": {
99
+ "bits": 4,
100
+ "group_size": 64
101
+ },
102
+ "model.layers.3.self_attn.q_proj": {
103
+ "bits": 4,
104
+ "group_size": 64
105
+ },
106
+ "model.layers.3.self_attn.k_proj": {
107
+ "bits": 4,
108
+ "group_size": 64
109
+ },
110
+ "model.layers.3.self_attn.v_proj": {
111
+ "bits": 8,
112
+ "group_size": 64
113
+ },
114
+ "model.layers.3.self_attn.o_proj": {
115
+ "bits": 8,
116
+ "group_size": 64
117
+ },
118
+ "model.layers.3.mlp.gate_proj": {
119
+ "bits": 8,
120
+ "group_size": 64
121
+ },
122
+ "model.layers.3.mlp.down_proj": {
123
+ "bits": 4,
124
+ "group_size": 64
125
+ },
126
+ "model.layers.3.mlp.up_proj": {
127
+ "bits": 4,
128
+ "group_size": 64
129
+ },
130
+ "model.layers.4.self_attn.q_proj": {
131
+ "bits": 4,
132
+ "group_size": 64
133
+ },
134
+ "model.layers.4.self_attn.k_proj": {
135
+ "bits": 4,
136
+ "group_size": 64
137
+ },
138
+ "model.layers.4.self_attn.v_proj": {
139
+ "bits": 8,
140
+ "group_size": 64
141
+ },
142
+ "model.layers.4.self_attn.o_proj": {
143
+ "bits": 8,
144
+ "group_size": 64
145
+ },
146
+ "model.layers.4.mlp.gate_proj": {
147
+ "bits": 4,
148
+ "group_size": 64
149
+ },
150
+ "model.layers.4.mlp.down_proj": {
151
+ "bits": 4,
152
+ "group_size": 64
153
+ },
154
+ "model.layers.4.mlp.up_proj": {
155
+ "bits": 4,
156
+ "group_size": 64
157
+ },
158
+ "model.layers.5.self_attn.q_proj": {
159
+ "bits": 4,
160
+ "group_size": 64
161
+ },
162
+ "model.layers.5.self_attn.k_proj": {
163
+ "bits": 4,
164
+ "group_size": 64
165
+ },
166
+ "model.layers.5.self_attn.v_proj": {
167
+ "bits": 8,
168
+ "group_size": 64
169
+ },
170
+ "model.layers.5.self_attn.o_proj": {
171
+ "bits": 8,
172
+ "group_size": 64
173
+ },
174
+ "model.layers.5.mlp.gate_proj": {
175
+ "bits": 4,
176
+ "group_size": 64
177
+ },
178
+ "model.layers.5.mlp.down_proj": {
179
+ "bits": 4,
180
+ "group_size": 64
181
+ },
182
+ "model.layers.5.mlp.up_proj": {
183
+ "bits": 4,
184
+ "group_size": 64
185
+ },
186
+ "model.layers.6.self_attn.q_proj": {
187
+ "bits": 4,
188
+ "group_size": 64
189
+ },
190
+ "model.layers.6.self_attn.k_proj": {
191
+ "bits": 4,
192
+ "group_size": 64
193
+ },
194
+ "model.layers.6.self_attn.v_proj": {
195
+ "bits": 8,
196
+ "group_size": 64
197
+ },
198
+ "model.layers.6.self_attn.o_proj": {
199
+ "bits": 8,
200
+ "group_size": 64
201
+ },
202
+ "model.layers.6.mlp.gate_proj": {
203
+ "bits": 4,
204
+ "group_size": 64
205
+ },
206
+ "model.layers.6.mlp.down_proj": {
207
+ "bits": 8,
208
+ "group_size": 64
209
+ },
210
+ "model.layers.6.mlp.up_proj": {
211
+ "bits": 4,
212
+ "group_size": 64
213
+ },
214
+ "model.layers.7.self_attn.q_proj": {
215
+ "bits": 4,
216
+ "group_size": 64
217
+ },
218
+ "model.layers.7.self_attn.k_proj": {
219
+ "bits": 8,
220
+ "group_size": 64
221
+ },
222
+ "model.layers.7.self_attn.v_proj": {
223
+ "bits": 8,
224
+ "group_size": 64
225
+ },
226
+ "model.layers.7.self_attn.o_proj": {
227
+ "bits": 4,
228
+ "group_size": 64
229
+ },
230
+ "model.layers.7.mlp.gate_proj": {
231
+ "bits": 4,
232
+ "group_size": 64
233
+ },
234
+ "model.layers.7.mlp.down_proj": {
235
+ "bits": 4,
236
+ "group_size": 64
237
+ },
238
+ "model.layers.7.mlp.up_proj": {
239
+ "bits": 4,
240
+ "group_size": 64
241
+ },
242
+ "model.layers.8.self_attn.q_proj": {
243
+ "bits": 4,
244
+ "group_size": 64
245
+ },
246
+ "model.layers.8.self_attn.k_proj": {
247
+ "bits": 4,
248
+ "group_size": 64
249
+ },
250
+ "model.layers.8.self_attn.v_proj": {
251
+ "bits": 8,
252
+ "group_size": 64
253
+ },
254
+ "model.layers.8.self_attn.o_proj": {
255
+ "bits": 8,
256
+ "group_size": 64
257
+ },
258
+ "model.layers.8.mlp.gate_proj": {
259
+ "bits": 4,
260
+ "group_size": 64
261
+ },
262
+ "model.layers.8.mlp.down_proj": {
263
+ "bits": 4,
264
+ "group_size": 64
265
+ },
266
+ "model.layers.8.mlp.up_proj": {
267
+ "bits": 4,
268
+ "group_size": 64
269
+ },
270
+ "model.layers.9.self_attn.q_proj": {
271
+ "bits": 4,
272
+ "group_size": 64
273
+ },
274
+ "model.layers.9.self_attn.k_proj": {
275
+ "bits": 8,
276
+ "group_size": 64
277
+ },
278
+ "model.layers.9.self_attn.v_proj": {
279
+ "bits": 8,
280
+ "group_size": 64
281
+ },
282
+ "model.layers.9.self_attn.o_proj": {
283
+ "bits": 4,
284
+ "group_size": 64
285
+ },
286
+ "model.layers.9.mlp.gate_proj": {
287
+ "bits": 4,
288
+ "group_size": 64
289
+ },
290
+ "model.layers.9.mlp.down_proj": {
291
+ "bits": 8,
292
+ "group_size": 64
293
+ },
294
+ "model.layers.9.mlp.up_proj": {
295
+ "bits": 4,
296
+ "group_size": 64
297
+ },
298
+ "model.layers.10.self_attn.q_proj": {
299
+ "bits": 4,
300
+ "group_size": 64
301
+ },
302
+ "model.layers.10.self_attn.k_proj": {
303
+ "bits": 8,
304
+ "group_size": 64
305
+ },
306
+ "model.layers.10.self_attn.v_proj": {
307
+ "bits": 8,
308
+ "group_size": 64
309
+ },
310
+ "model.layers.10.self_attn.o_proj": {
311
+ "bits": 4,
312
+ "group_size": 64
313
+ },
314
+ "model.layers.10.mlp.gate_proj": {
315
+ "bits": 4,
316
+ "group_size": 64
317
+ },
318
+ "model.layers.10.mlp.down_proj": {
319
+ "bits": 4,
320
+ "group_size": 64
321
+ },
322
+ "model.layers.10.mlp.up_proj": {
323
+ "bits": 4,
324
+ "group_size": 64
325
+ },
326
+ "model.layers.11.self_attn.q_proj": {
327
+ "bits": 4,
328
+ "group_size": 64
329
+ },
330
+ "model.layers.11.self_attn.k_proj": {
331
+ "bits": 4,
332
+ "group_size": 64
333
+ },
334
+ "model.layers.11.self_attn.v_proj": {
335
+ "bits": 8,
336
+ "group_size": 64
337
+ },
338
+ "model.layers.11.self_attn.o_proj": {
339
+ "bits": 8,
340
+ "group_size": 64
341
+ },
342
+ "model.layers.11.mlp.gate_proj": {
343
+ "bits": 4,
344
+ "group_size": 64
345
+ },
346
+ "model.layers.11.mlp.down_proj": {
347
+ "bits": 4,
348
+ "group_size": 64
349
+ },
350
+ "model.layers.11.mlp.up_proj": {
351
+ "bits": 4,
352
+ "group_size": 64
353
+ },
354
+ "model.layers.12.self_attn.q_proj": {
355
+ "bits": 4,
356
+ "group_size": 64
357
+ },
358
+ "model.layers.12.self_attn.k_proj": {
359
+ "bits": 4,
360
+ "group_size": 64
361
+ },
362
+ "model.layers.12.self_attn.v_proj": {
363
+ "bits": 8,
364
+ "group_size": 64
365
+ },
366
+ "model.layers.12.self_attn.o_proj": {
367
+ "bits": 8,
368
+ "group_size": 64
369
+ },
370
+ "model.layers.12.mlp.gate_proj": {
371
+ "bits": 4,
372
+ "group_size": 64
373
+ },
374
+ "model.layers.12.mlp.down_proj": {
375
+ "bits": 8,
376
+ "group_size": 64
377
+ },
378
+ "model.layers.12.mlp.up_proj": {
379
+ "bits": 4,
380
+ "group_size": 64
381
+ },
382
+ "model.layers.13.self_attn.q_proj": {
383
+ "bits": 4,
384
+ "group_size": 64
385
+ },
386
+ "model.layers.13.self_attn.k_proj": {
387
+ "bits": 4,
388
+ "group_size": 64
389
+ },
390
+ "model.layers.13.self_attn.v_proj": {
391
+ "bits": 8,
392
+ "group_size": 64
393
+ },
394
+ "model.layers.13.self_attn.o_proj": {
395
+ "bits": 8,
396
+ "group_size": 64
397
+ },
398
+ "model.layers.13.mlp.gate_proj": {
399
+ "bits": 4,
400
+ "group_size": 64
401
+ },
402
+ "model.layers.13.mlp.down_proj": {
403
+ "bits": 4,
404
+ "group_size": 64
405
+ },
406
+ "model.layers.13.mlp.up_proj": {
407
+ "bits": 4,
408
+ "group_size": 64
409
+ },
410
+ "model.layers.14.self_attn.q_proj": {
411
+ "bits": 8,
412
+ "group_size": 64
413
+ },
414
+ "model.layers.14.self_attn.k_proj": {
415
+ "bits": 4,
416
+ "group_size": 64
417
+ },
418
+ "model.layers.14.self_attn.v_proj": {
419
+ "bits": 8,
420
+ "group_size": 64
421
+ },
422
+ "model.layers.14.self_attn.o_proj": {
423
+ "bits": 4,
424
+ "group_size": 64
425
+ },
426
+ "model.layers.14.mlp.gate_proj": {
427
+ "bits": 4,
428
+ "group_size": 64
429
+ },
430
+ "model.layers.14.mlp.down_proj": {
431
+ "bits": 4,
432
+ "group_size": 64
433
+ },
434
+ "model.layers.14.mlp.up_proj": {
435
+ "bits": 4,
436
+ "group_size": 64
437
+ },
438
+ "model.layers.15.self_attn.q_proj": {
439
+ "bits": 4,
440
+ "group_size": 64
441
+ },
442
+ "model.layers.15.self_attn.k_proj": {
443
+ "bits": 4,
444
+ "group_size": 64
445
+ },
446
+ "model.layers.15.self_attn.v_proj": {
447
+ "bits": 8,
448
+ "group_size": 64
449
+ },
450
+ "model.layers.15.self_attn.o_proj": {
451
+ "bits": 8,
452
+ "group_size": 64
453
+ },
454
+ "model.layers.15.mlp.gate_proj": {
455
+ "bits": 4,
456
+ "group_size": 64
457
+ },
458
+ "model.layers.15.mlp.down_proj": {
459
+ "bits": 4,
460
+ "group_size": 64
461
+ },
462
+ "model.layers.15.mlp.up_proj": {
463
+ "bits": 8,
464
+ "group_size": 64
465
+ },
466
+ "model.layers.16.self_attn.q_proj": {
467
+ "bits": 4,
468
+ "group_size": 64
469
+ },
470
+ "model.layers.16.self_attn.k_proj": {
471
+ "bits": 4,
472
+ "group_size": 64
473
+ },
474
+ "model.layers.16.self_attn.v_proj": {
475
+ "bits": 8,
476
+ "group_size": 64
477
+ },
478
+ "model.layers.16.self_attn.o_proj": {
479
+ "bits": 8,
480
+ "group_size": 64
481
+ },
482
+ "model.layers.16.mlp.gate_proj": {
483
+ "bits": 4,
484
+ "group_size": 64
485
+ },
486
+ "model.layers.16.mlp.down_proj": {
487
+ "bits": 4,
488
+ "group_size": 64
489
+ },
490
+ "model.layers.16.mlp.up_proj": {
491
+ "bits": 4,
492
+ "group_size": 64
493
+ },
494
+ "model.layers.17.self_attn.q_proj": {
495
+ "bits": 4,
496
+ "group_size": 64
497
+ },
498
+ "model.layers.17.self_attn.k_proj": {
499
+ "bits": 4,
500
+ "group_size": 64
501
+ },
502
+ "model.layers.17.self_attn.v_proj": {
503
+ "bits": 8,
504
+ "group_size": 64
505
+ },
506
+ "model.layers.17.self_attn.o_proj": {
507
+ "bits": 8,
508
+ "group_size": 64
509
+ },
510
+ "model.layers.17.mlp.gate_proj": {
511
+ "bits": 4,
512
+ "group_size": 64
513
+ },
514
+ "model.layers.17.mlp.down_proj": {
515
+ "bits": 4,
516
+ "group_size": 64
517
+ },
518
+ "model.layers.17.mlp.up_proj": {
519
+ "bits": 4,
520
+ "group_size": 64
521
+ },
522
+ "model.layers.18.self_attn.q_proj": {
523
+ "bits": 4,
524
+ "group_size": 64
525
+ },
526
+ "model.layers.18.self_attn.k_proj": {
527
+ "bits": 4,
528
+ "group_size": 64
529
+ },
530
+ "model.layers.18.self_attn.v_proj": {
531
+ "bits": 8,
532
+ "group_size": 64
533
+ },
534
+ "model.layers.18.self_attn.o_proj": {
535
+ "bits": 8,
536
+ "group_size": 64
537
+ },
538
+ "model.layers.18.mlp.gate_proj": {
539
+ "bits": 4,
540
+ "group_size": 64
541
+ },
542
+ "model.layers.18.mlp.down_proj": {
543
+ "bits": 4,
544
+ "group_size": 64
545
+ },
546
+ "model.layers.18.mlp.up_proj": {
547
+ "bits": 8,
548
+ "group_size": 64
549
+ },
550
+ "model.layers.19.self_attn.q_proj": {
551
+ "bits": 8,
552
+ "group_size": 64
553
+ },
554
+ "model.layers.19.self_attn.k_proj": {
555
+ "bits": 4,
556
+ "group_size": 64
557
+ },
558
+ "model.layers.19.self_attn.v_proj": {
559
+ "bits": 8,
560
+ "group_size": 64
561
+ },
562
+ "model.layers.19.self_attn.o_proj": {
563
+ "bits": 4,
564
+ "group_size": 64
565
+ },
566
+ "model.layers.19.mlp.gate_proj": {
567
+ "bits": 4,
568
+ "group_size": 64
569
+ },
570
+ "model.layers.19.mlp.down_proj": {
571
+ "bits": 4,
572
+ "group_size": 64
573
+ },
574
+ "model.layers.19.mlp.up_proj": {
575
+ "bits": 4,
576
+ "group_size": 64
577
+ },
578
+ "model.layers.20.self_attn.q_proj": {
579
+ "bits": 4,
580
+ "group_size": 64
581
+ },
582
+ "model.layers.20.self_attn.k_proj": {
583
+ "bits": 4,
584
+ "group_size": 64
585
+ },
586
+ "model.layers.20.self_attn.v_proj": {
587
+ "bits": 8,
588
+ "group_size": 64
589
+ },
590
+ "model.layers.20.self_attn.o_proj": {
591
+ "bits": 8,
592
+ "group_size": 64
593
+ },
594
+ "model.layers.20.mlp.gate_proj": {
595
+ "bits": 4,
596
+ "group_size": 64
597
+ },
598
+ "model.layers.20.mlp.down_proj": {
599
+ "bits": 4,
600
+ "group_size": 64
601
+ },
602
+ "model.layers.20.mlp.up_proj": {
603
+ "bits": 4,
604
+ "group_size": 64
605
+ },
606
+ "model.layers.21.self_attn.q_proj": {
607
+ "bits": 8,
608
+ "group_size": 64
609
+ },
610
+ "model.layers.21.self_attn.k_proj": {
611
+ "bits": 4,
612
+ "group_size": 64
613
+ },
614
+ "model.layers.21.self_attn.v_proj": {
615
+ "bits": 8,
616
+ "group_size": 64
617
+ },
618
+ "model.layers.21.self_attn.o_proj": {
619
+ "bits": 4,
620
+ "group_size": 64
621
+ },
622
+ "model.layers.21.mlp.gate_proj": {
623
+ "bits": 4,
624
+ "group_size": 64
625
+ },
626
+ "model.layers.21.mlp.down_proj": {
627
+ "bits": 4,
628
+ "group_size": 64
629
+ },
630
+ "model.layers.21.mlp.up_proj": {
631
+ "bits": 8,
632
+ "group_size": 64
633
+ },
634
+ "model.layers.22.self_attn.q_proj": {
635
+ "bits": 4,
636
+ "group_size": 64
637
+ },
638
+ "model.layers.22.self_attn.k_proj": {
639
+ "bits": 4,
640
+ "group_size": 64
641
+ },
642
+ "model.layers.22.self_attn.v_proj": {
643
+ "bits": 8,
644
+ "group_size": 64
645
+ },
646
+ "model.layers.22.self_attn.o_proj": {
647
+ "bits": 8,
648
+ "group_size": 64
649
+ },
650
+ "model.layers.22.mlp.gate_proj": {
651
+ "bits": 4,
652
+ "group_size": 64
653
+ },
654
+ "model.layers.22.mlp.down_proj": {
655
+ "bits": 4,
656
+ "group_size": 64
657
+ },
658
+ "model.layers.22.mlp.up_proj": {
659
+ "bits": 4,
660
+ "group_size": 64
661
+ },
662
+ "model.layers.23.self_attn.q_proj": {
663
+ "bits": 4,
664
+ "group_size": 64
665
+ },
666
+ "model.layers.23.self_attn.k_proj": {
667
+ "bits": 4,
668
+ "group_size": 64
669
+ },
670
+ "model.layers.23.self_attn.v_proj": {
671
+ "bits": 8,
672
+ "group_size": 64
673
+ },
674
+ "model.layers.23.self_attn.o_proj": {
675
+ "bits": 8,
676
+ "group_size": 64
677
+ },
678
+ "model.layers.23.mlp.gate_proj": {
679
+ "bits": 4,
680
+ "group_size": 64
681
+ },
682
+ "model.layers.23.mlp.down_proj": {
683
+ "bits": 4,
684
+ "group_size": 64
685
+ },
686
+ "model.layers.23.mlp.up_proj": {
687
+ "bits": 4,
688
+ "group_size": 64
689
+ },
690
+ "model.layers.24.self_attn.q_proj": {
691
+ "bits": 4,
692
+ "group_size": 64
693
+ },
694
+ "model.layers.24.self_attn.k_proj": {
695
+ "bits": 4,
696
+ "group_size": 64
697
+ },
698
+ "model.layers.24.self_attn.v_proj": {
699
+ "bits": 8,
700
+ "group_size": 64
701
+ },
702
+ "model.layers.24.self_attn.o_proj": {
703
+ "bits": 8,
704
+ "group_size": 64
705
+ },
706
+ "model.layers.24.mlp.gate_proj": {
707
+ "bits": 4,
708
+ "group_size": 64
709
+ },
710
+ "model.layers.24.mlp.down_proj": {
711
+ "bits": 4,
712
+ "group_size": 64
713
+ },
714
+ "model.layers.24.mlp.up_proj": {
715
+ "bits": 8,
716
+ "group_size": 64
717
+ },
718
+ "model.layers.25.self_attn.q_proj": {
719
+ "bits": 4,
720
+ "group_size": 64
721
+ },
722
+ "model.layers.25.self_attn.k_proj": {
723
+ "bits": 8,
724
+ "group_size": 64
725
+ },
726
+ "model.layers.25.self_attn.v_proj": {
727
+ "bits": 8,
728
+ "group_size": 64
729
+ },
730
+ "model.layers.25.self_attn.o_proj": {
731
+ "bits": 4,
732
+ "group_size": 64
733
+ },
734
+ "model.layers.25.mlp.gate_proj": {
735
+ "bits": 4,
736
+ "group_size": 64
737
+ },
738
+ "model.layers.25.mlp.down_proj": {
739
+ "bits": 4,
740
+ "group_size": 64
741
+ },
742
+ "model.layers.25.mlp.up_proj": {
743
+ "bits": 4,
744
+ "group_size": 64
745
+ },
746
+ "model.layers.26.self_attn.q_proj": {
747
+ "bits": 4,
748
+ "group_size": 64
749
+ },
750
+ "model.layers.26.self_attn.k_proj": {
751
+ "bits": 8,
752
+ "group_size": 64
753
+ },
754
+ "model.layers.26.self_attn.v_proj": {
755
+ "bits": 8,
756
+ "group_size": 64
757
+ },
758
+ "model.layers.26.self_attn.o_proj": {
759
+ "bits": 4,
760
+ "group_size": 64
761
+ },
762
+ "model.layers.26.mlp.gate_proj": {
763
+ "bits": 4,
764
+ "group_size": 64
765
+ },
766
+ "model.layers.26.mlp.down_proj": {
767
+ "bits": 4,
768
+ "group_size": 64
769
+ },
770
+ "model.layers.26.mlp.up_proj": {
771
+ "bits": 4,
772
+ "group_size": 64
773
+ },
774
+ "model.layers.27.self_attn.q_proj": {
775
+ "bits": 4,
776
+ "group_size": 64
777
+ },
778
+ "model.layers.27.self_attn.k_proj": {
779
+ "bits": 8,
780
+ "group_size": 64
781
+ },
782
+ "model.layers.27.self_attn.v_proj": {
783
+ "bits": 8,
784
+ "group_size": 64
785
+ },
786
+ "model.layers.27.self_attn.o_proj": {
787
+ "bits": 4,
788
+ "group_size": 64
789
+ },
790
+ "model.layers.27.mlp.gate_proj": {
791
+ "bits": 4,
792
+ "group_size": 64
793
+ },
794
+ "model.layers.27.mlp.down_proj": {
795
+ "bits": 8,
796
+ "group_size": 64
797
+ },
798
+ "model.layers.27.mlp.up_proj": {
799
+ "bits": 4,
800
+ "group_size": 64
801
+ },
802
+ "model.layers.28.self_attn.q_proj": {
803
+ "bits": 8,
804
+ "group_size": 64
805
+ },
806
+ "model.layers.28.self_attn.k_proj": {
807
+ "bits": 8,
808
+ "group_size": 64
809
+ },
810
+ "model.layers.28.self_attn.v_proj": {
811
+ "bits": 4,
812
+ "group_size": 64
813
+ },
814
+ "model.layers.28.self_attn.o_proj": {
815
+ "bits": 4,
816
+ "group_size": 64
817
+ },
818
+ "model.layers.28.mlp.gate_proj": {
819
+ "bits": 4,
820
+ "group_size": 64
821
+ },
822
+ "model.layers.28.mlp.down_proj": {
823
+ "bits": 4,
824
+ "group_size": 64
825
+ },
826
+ "model.layers.28.mlp.up_proj": {
827
+ "bits": 4,
828
+ "group_size": 64
829
+ },
830
+ "model.layers.29.self_attn.q_proj": {
831
+ "bits": 4,
832
+ "group_size": 64
833
+ },
834
+ "model.layers.29.self_attn.k_proj": {
835
+ "bits": 8,
836
+ "group_size": 64
837
+ },
838
+ "model.layers.29.self_attn.v_proj": {
839
+ "bits": 8,
840
+ "group_size": 64
841
+ },
842
+ "model.layers.29.self_attn.o_proj": {
843
+ "bits": 4,
844
+ "group_size": 64
845
+ },
846
+ "model.layers.29.mlp.gate_proj": {
847
+ "bits": 4,
848
+ "group_size": 64
849
+ },
850
+ "model.layers.29.mlp.down_proj": {
851
+ "bits": 4,
852
+ "group_size": 64
853
+ },
854
+ "model.layers.29.mlp.up_proj": {
855
+ "bits": 4,
856
+ "group_size": 64
857
+ },
858
+ "model.layers.30.self_attn.q_proj": {
859
+ "bits": 4,
860
+ "group_size": 64
861
+ },
862
+ "model.layers.30.self_attn.k_proj": {
863
+ "bits": 8,
864
+ "group_size": 64
865
+ },
866
+ "model.layers.30.self_attn.v_proj": {
867
+ "bits": 8,
868
+ "group_size": 64
869
+ },
870
+ "model.layers.30.self_attn.o_proj": {
871
+ "bits": 4,
872
+ "group_size": 64
873
+ },
874
+ "model.layers.30.mlp.gate_proj": {
875
+ "bits": 8,
876
+ "group_size": 64
877
+ },
878
+ "model.layers.30.mlp.down_proj": {
879
+ "bits": 4,
880
+ "group_size": 64
881
+ },
882
+ "model.layers.30.mlp.up_proj": {
883
+ "bits": 4,
884
+ "group_size": 64
885
+ },
886
+ "model.layers.31.self_attn.q_proj": {
887
+ "bits": 4,
888
+ "group_size": 64
889
+ },
890
+ "model.layers.31.self_attn.k_proj": {
891
+ "bits": 8,
892
+ "group_size": 64
893
+ },
894
+ "model.layers.31.self_attn.v_proj": {
895
+ "bits": 8,
896
+ "group_size": 64
897
+ },
898
+ "model.layers.31.self_attn.o_proj": {
899
+ "bits": 4,
900
+ "group_size": 64
901
+ },
902
+ "model.layers.31.mlp.gate_proj": {
903
+ "bits": 4,
904
+ "group_size": 64
905
+ },
906
+ "model.layers.31.mlp.down_proj": {
907
+ "bits": 4,
908
+ "group_size": 64
909
+ },
910
+ "model.layers.31.mlp.up_proj": {
911
+ "bits": 4,
912
+ "group_size": 64
913
+ },
914
+ "model.layers.32.self_attn.q_proj": {
915
+ "bits": 8,
916
+ "group_size": 64
917
+ },
918
+ "model.layers.32.self_attn.k_proj": {
919
+ "bits": 8,
920
+ "group_size": 64
921
+ },
922
+ "model.layers.32.self_attn.v_proj": {
923
+ "bits": 4,
924
+ "group_size": 64
925
+ },
926
+ "model.layers.32.self_attn.o_proj": {
927
+ "bits": 4,
928
+ "group_size": 64
929
+ },
930
+ "model.layers.32.mlp.gate_proj": {
931
+ "bits": 4,
932
+ "group_size": 64
933
+ },
934
+ "model.layers.32.mlp.down_proj": {
935
+ "bits": 4,
936
+ "group_size": 64
937
+ },
938
+ "model.layers.32.mlp.up_proj": {
939
+ "bits": 4,
940
+ "group_size": 64
941
+ },
942
+ "model.layers.33.self_attn.q_proj": {
943
+ "bits": 4,
944
+ "group_size": 64
945
+ },
946
+ "model.layers.33.self_attn.k_proj": {
947
+ "bits": 8,
948
+ "group_size": 64
949
+ },
950
+ "model.layers.33.self_attn.v_proj": {
951
+ "bits": 8,
952
+ "group_size": 64
953
+ },
954
+ "model.layers.33.self_attn.o_proj": {
955
+ "bits": 4,
956
+ "group_size": 64
957
+ },
958
+ "model.layers.33.mlp.gate_proj": {
959
+ "bits": 4,
960
+ "group_size": 64
961
+ },
962
+ "model.layers.33.mlp.down_proj": {
963
+ "bits": 4,
964
+ "group_size": 64
965
+ },
966
+ "model.layers.33.mlp.up_proj": {
967
+ "bits": 8,
968
+ "group_size": 64
969
+ },
970
+ "model.layers.34.self_attn.q_proj": {
971
+ "bits": 8,
972
+ "group_size": 64
973
+ },
974
+ "model.layers.34.self_attn.k_proj": {
975
+ "bits": 4,
976
+ "group_size": 64
977
+ },
978
+ "model.layers.34.self_attn.v_proj": {
979
+ "bits": 8,
980
+ "group_size": 64
981
+ },
982
+ "model.layers.34.self_attn.o_proj": {
983
+ "bits": 4,
984
+ "group_size": 64
985
+ },
986
+ "model.layers.34.mlp.gate_proj": {
987
+ "bits": 4,
988
+ "group_size": 64
989
+ },
990
+ "model.layers.34.mlp.down_proj": {
991
+ "bits": 4,
992
+ "group_size": 64
993
+ },
994
+ "model.layers.34.mlp.up_proj": {
995
+ "bits": 4,
996
+ "group_size": 64
997
+ },
998
+ "model.layers.35.self_attn.q_proj": {
999
+ "bits": 4,
1000
+ "group_size": 64
1001
+ },
1002
+ "model.layers.35.self_attn.k_proj": {
1003
+ "bits": 8,
1004
+ "group_size": 64
1005
+ },
1006
+ "model.layers.35.self_attn.v_proj": {
1007
+ "bits": 8,
1008
+ "group_size": 64
1009
+ },
1010
+ "model.layers.35.self_attn.o_proj": {
1011
+ "bits": 8,
1012
+ "group_size": 64
1013
+ },
1014
+ "model.layers.35.mlp.gate_proj": {
1015
+ "bits": 8,
1016
+ "group_size": 64
1017
+ },
1018
+ "model.layers.35.mlp.down_proj": {
1019
+ "bits": 8,
1020
+ "group_size": 64
1021
+ },
1022
+ "model.layers.35.mlp.up_proj": {
1023
+ "bits": 8,
1024
+ "group_size": 64
1025
+ },
1026
+ "lm_head": {
1027
+ "bits": 8,
1028
+ "group_size": 64
1029
+ }
1030
+ },
1031
+ "quantization_config": {
1032
+ "group_size": 64,
1033
+ "bits": 4,
1034
+ "mode": "affine",
1035
+ "model.embed_tokens": {
1036
+ "bits": 8,
1037
+ "group_size": 64
1038
+ },
1039
+ "model.layers.0.self_attn.q_proj": {
1040
+ "bits": 4,
1041
+ "group_size": 64
1042
+ },
1043
+ "model.layers.0.self_attn.k_proj": {
1044
+ "bits": 4,
1045
+ "group_size": 64
1046
+ },
1047
+ "model.layers.0.self_attn.v_proj": {
1048
+ "bits": 8,
1049
+ "group_size": 64
1050
+ },
1051
+ "model.layers.0.self_attn.o_proj": {
1052
+ "bits": 8,
1053
+ "group_size": 64
1054
+ },
1055
+ "model.layers.0.mlp.gate_proj": {
1056
+ "bits": 4,
1057
+ "group_size": 64
1058
+ },
1059
+ "model.layers.0.mlp.down_proj": {
1060
+ "bits": 8,
1061
+ "group_size": 64
1062
+ },
1063
+ "model.layers.0.mlp.up_proj": {
1064
+ "bits": 4,
1065
+ "group_size": 64
1066
+ },
1067
+ "model.layers.1.self_attn.q_proj": {
1068
+ "bits": 4,
1069
+ "group_size": 64
1070
+ },
1071
+ "model.layers.1.self_attn.k_proj": {
1072
+ "bits": 4,
1073
+ "group_size": 64
1074
+ },
1075
+ "model.layers.1.self_attn.v_proj": {
1076
+ "bits": 8,
1077
+ "group_size": 64
1078
+ },
1079
+ "model.layers.1.self_attn.o_proj": {
1080
+ "bits": 8,
1081
+ "group_size": 64
1082
+ },
1083
+ "model.layers.1.mlp.gate_proj": {
1084
+ "bits": 4,
1085
+ "group_size": 64
1086
+ },
1087
+ "model.layers.1.mlp.down_proj": {
1088
+ "bits": 4,
1089
+ "group_size": 64
1090
+ },
1091
+ "model.layers.1.mlp.up_proj": {
1092
+ "bits": 4,
1093
+ "group_size": 64
1094
+ },
1095
+ "model.layers.2.self_attn.q_proj": {
1096
+ "bits": 8,
1097
+ "group_size": 64
1098
+ },
1099
+ "model.layers.2.self_attn.k_proj": {
1100
+ "bits": 4,
1101
+ "group_size": 64
1102
+ },
1103
+ "model.layers.2.self_attn.v_proj": {
1104
+ "bits": 8,
1105
+ "group_size": 64
1106
+ },
1107
+ "model.layers.2.self_attn.o_proj": {
1108
+ "bits": 4,
1109
+ "group_size": 64
1110
+ },
1111
+ "model.layers.2.mlp.gate_proj": {
1112
+ "bits": 4,
1113
+ "group_size": 64
1114
+ },
1115
+ "model.layers.2.mlp.down_proj": {
1116
+ "bits": 4,
1117
+ "group_size": 64
1118
+ },
1119
+ "model.layers.2.mlp.up_proj": {
1120
+ "bits": 4,
1121
+ "group_size": 64
1122
+ },
1123
+ "model.layers.3.self_attn.q_proj": {
1124
+ "bits": 4,
1125
+ "group_size": 64
1126
+ },
1127
+ "model.layers.3.self_attn.k_proj": {
1128
+ "bits": 4,
1129
+ "group_size": 64
1130
+ },
1131
+ "model.layers.3.self_attn.v_proj": {
1132
+ "bits": 8,
1133
+ "group_size": 64
1134
+ },
1135
+ "model.layers.3.self_attn.o_proj": {
1136
+ "bits": 8,
1137
+ "group_size": 64
1138
+ },
1139
+ "model.layers.3.mlp.gate_proj": {
1140
+ "bits": 8,
1141
+ "group_size": 64
1142
+ },
1143
+ "model.layers.3.mlp.down_proj": {
1144
+ "bits": 4,
1145
+ "group_size": 64
1146
+ },
1147
+ "model.layers.3.mlp.up_proj": {
1148
+ "bits": 4,
1149
+ "group_size": 64
1150
+ },
1151
+ "model.layers.4.self_attn.q_proj": {
1152
+ "bits": 4,
1153
+ "group_size": 64
1154
+ },
1155
+ "model.layers.4.self_attn.k_proj": {
1156
+ "bits": 4,
1157
+ "group_size": 64
1158
+ },
1159
+ "model.layers.4.self_attn.v_proj": {
1160
+ "bits": 8,
1161
+ "group_size": 64
1162
+ },
1163
+ "model.layers.4.self_attn.o_proj": {
1164
+ "bits": 8,
1165
+ "group_size": 64
1166
+ },
1167
+ "model.layers.4.mlp.gate_proj": {
1168
+ "bits": 4,
1169
+ "group_size": 64
1170
+ },
1171
+ "model.layers.4.mlp.down_proj": {
1172
+ "bits": 4,
1173
+ "group_size": 64
1174
+ },
1175
+ "model.layers.4.mlp.up_proj": {
1176
+ "bits": 4,
1177
+ "group_size": 64
1178
+ },
1179
+ "model.layers.5.self_attn.q_proj": {
1180
+ "bits": 4,
1181
+ "group_size": 64
1182
+ },
1183
+ "model.layers.5.self_attn.k_proj": {
1184
+ "bits": 4,
1185
+ "group_size": 64
1186
+ },
1187
+ "model.layers.5.self_attn.v_proj": {
1188
+ "bits": 8,
1189
+ "group_size": 64
1190
+ },
1191
+ "model.layers.5.self_attn.o_proj": {
1192
+ "bits": 8,
1193
+ "group_size": 64
1194
+ },
1195
+ "model.layers.5.mlp.gate_proj": {
1196
+ "bits": 4,
1197
+ "group_size": 64
1198
+ },
1199
+ "model.layers.5.mlp.down_proj": {
1200
+ "bits": 4,
1201
+ "group_size": 64
1202
+ },
1203
+ "model.layers.5.mlp.up_proj": {
1204
+ "bits": 4,
1205
+ "group_size": 64
1206
+ },
1207
+ "model.layers.6.self_attn.q_proj": {
1208
+ "bits": 4,
1209
+ "group_size": 64
1210
+ },
1211
+ "model.layers.6.self_attn.k_proj": {
1212
+ "bits": 4,
1213
+ "group_size": 64
1214
+ },
1215
+ "model.layers.6.self_attn.v_proj": {
1216
+ "bits": 8,
1217
+ "group_size": 64
1218
+ },
1219
+ "model.layers.6.self_attn.o_proj": {
1220
+ "bits": 8,
1221
+ "group_size": 64
1222
+ },
1223
+ "model.layers.6.mlp.gate_proj": {
1224
+ "bits": 4,
1225
+ "group_size": 64
1226
+ },
1227
+ "model.layers.6.mlp.down_proj": {
1228
+ "bits": 8,
1229
+ "group_size": 64
1230
+ },
1231
+ "model.layers.6.mlp.up_proj": {
1232
+ "bits": 4,
1233
+ "group_size": 64
1234
+ },
1235
+ "model.layers.7.self_attn.q_proj": {
1236
+ "bits": 4,
1237
+ "group_size": 64
1238
+ },
1239
+ "model.layers.7.self_attn.k_proj": {
1240
+ "bits": 8,
1241
+ "group_size": 64
1242
+ },
1243
+ "model.layers.7.self_attn.v_proj": {
1244
+ "bits": 8,
1245
+ "group_size": 64
1246
+ },
1247
+ "model.layers.7.self_attn.o_proj": {
1248
+ "bits": 4,
1249
+ "group_size": 64
1250
+ },
1251
+ "model.layers.7.mlp.gate_proj": {
1252
+ "bits": 4,
1253
+ "group_size": 64
1254
+ },
1255
+ "model.layers.7.mlp.down_proj": {
1256
+ "bits": 4,
1257
+ "group_size": 64
1258
+ },
1259
+ "model.layers.7.mlp.up_proj": {
1260
+ "bits": 4,
1261
+ "group_size": 64
1262
+ },
1263
+ "model.layers.8.self_attn.q_proj": {
1264
+ "bits": 4,
1265
+ "group_size": 64
1266
+ },
1267
+ "model.layers.8.self_attn.k_proj": {
1268
+ "bits": 4,
1269
+ "group_size": 64
1270
+ },
1271
+ "model.layers.8.self_attn.v_proj": {
1272
+ "bits": 8,
1273
+ "group_size": 64
1274
+ },
1275
+ "model.layers.8.self_attn.o_proj": {
1276
+ "bits": 8,
1277
+ "group_size": 64
1278
+ },
1279
+ "model.layers.8.mlp.gate_proj": {
1280
+ "bits": 4,
1281
+ "group_size": 64
1282
+ },
1283
+ "model.layers.8.mlp.down_proj": {
1284
+ "bits": 4,
1285
+ "group_size": 64
1286
+ },
1287
+ "model.layers.8.mlp.up_proj": {
1288
+ "bits": 4,
1289
+ "group_size": 64
1290
+ },
1291
+ "model.layers.9.self_attn.q_proj": {
1292
+ "bits": 4,
1293
+ "group_size": 64
1294
+ },
1295
+ "model.layers.9.self_attn.k_proj": {
1296
+ "bits": 8,
1297
+ "group_size": 64
1298
+ },
1299
+ "model.layers.9.self_attn.v_proj": {
1300
+ "bits": 8,
1301
+ "group_size": 64
1302
+ },
1303
+ "model.layers.9.self_attn.o_proj": {
1304
+ "bits": 4,
1305
+ "group_size": 64
1306
+ },
1307
+ "model.layers.9.mlp.gate_proj": {
1308
+ "bits": 4,
1309
+ "group_size": 64
1310
+ },
1311
+ "model.layers.9.mlp.down_proj": {
1312
+ "bits": 8,
1313
+ "group_size": 64
1314
+ },
1315
+ "model.layers.9.mlp.up_proj": {
1316
+ "bits": 4,
1317
+ "group_size": 64
1318
+ },
1319
+ "model.layers.10.self_attn.q_proj": {
1320
+ "bits": 4,
1321
+ "group_size": 64
1322
+ },
1323
+ "model.layers.10.self_attn.k_proj": {
1324
+ "bits": 8,
1325
+ "group_size": 64
1326
+ },
1327
+ "model.layers.10.self_attn.v_proj": {
1328
+ "bits": 8,
1329
+ "group_size": 64
1330
+ },
1331
+ "model.layers.10.self_attn.o_proj": {
1332
+ "bits": 4,
1333
+ "group_size": 64
1334
+ },
1335
+ "model.layers.10.mlp.gate_proj": {
1336
+ "bits": 4,
1337
+ "group_size": 64
1338
+ },
1339
+ "model.layers.10.mlp.down_proj": {
1340
+ "bits": 4,
1341
+ "group_size": 64
1342
+ },
1343
+ "model.layers.10.mlp.up_proj": {
1344
+ "bits": 4,
1345
+ "group_size": 64
1346
+ },
1347
+ "model.layers.11.self_attn.q_proj": {
1348
+ "bits": 4,
1349
+ "group_size": 64
1350
+ },
1351
+ "model.layers.11.self_attn.k_proj": {
1352
+ "bits": 4,
1353
+ "group_size": 64
1354
+ },
1355
+ "model.layers.11.self_attn.v_proj": {
1356
+ "bits": 8,
1357
+ "group_size": 64
1358
+ },
1359
+ "model.layers.11.self_attn.o_proj": {
1360
+ "bits": 8,
1361
+ "group_size": 64
1362
+ },
1363
+ "model.layers.11.mlp.gate_proj": {
1364
+ "bits": 4,
1365
+ "group_size": 64
1366
+ },
1367
+ "model.layers.11.mlp.down_proj": {
1368
+ "bits": 4,
1369
+ "group_size": 64
1370
+ },
1371
+ "model.layers.11.mlp.up_proj": {
1372
+ "bits": 4,
1373
+ "group_size": 64
1374
+ },
1375
+ "model.layers.12.self_attn.q_proj": {
1376
+ "bits": 4,
1377
+ "group_size": 64
1378
+ },
1379
+ "model.layers.12.self_attn.k_proj": {
1380
+ "bits": 4,
1381
+ "group_size": 64
1382
+ },
1383
+ "model.layers.12.self_attn.v_proj": {
1384
+ "bits": 8,
1385
+ "group_size": 64
1386
+ },
1387
+ "model.layers.12.self_attn.o_proj": {
1388
+ "bits": 8,
1389
+ "group_size": 64
1390
+ },
1391
+ "model.layers.12.mlp.gate_proj": {
1392
+ "bits": 4,
1393
+ "group_size": 64
1394
+ },
1395
+ "model.layers.12.mlp.down_proj": {
1396
+ "bits": 8,
1397
+ "group_size": 64
1398
+ },
1399
+ "model.layers.12.mlp.up_proj": {
1400
+ "bits": 4,
1401
+ "group_size": 64
1402
+ },
1403
+ "model.layers.13.self_attn.q_proj": {
1404
+ "bits": 4,
1405
+ "group_size": 64
1406
+ },
1407
+ "model.layers.13.self_attn.k_proj": {
1408
+ "bits": 4,
1409
+ "group_size": 64
1410
+ },
1411
+ "model.layers.13.self_attn.v_proj": {
1412
+ "bits": 8,
1413
+ "group_size": 64
1414
+ },
1415
+ "model.layers.13.self_attn.o_proj": {
1416
+ "bits": 8,
1417
+ "group_size": 64
1418
+ },
1419
+ "model.layers.13.mlp.gate_proj": {
1420
+ "bits": 4,
1421
+ "group_size": 64
1422
+ },
1423
+ "model.layers.13.mlp.down_proj": {
1424
+ "bits": 4,
1425
+ "group_size": 64
1426
+ },
1427
+ "model.layers.13.mlp.up_proj": {
1428
+ "bits": 4,
1429
+ "group_size": 64
1430
+ },
1431
+ "model.layers.14.self_attn.q_proj": {
1432
+ "bits": 8,
1433
+ "group_size": 64
1434
+ },
1435
+ "model.layers.14.self_attn.k_proj": {
1436
+ "bits": 4,
1437
+ "group_size": 64
1438
+ },
1439
+ "model.layers.14.self_attn.v_proj": {
1440
+ "bits": 8,
1441
+ "group_size": 64
1442
+ },
1443
+ "model.layers.14.self_attn.o_proj": {
1444
+ "bits": 4,
1445
+ "group_size": 64
1446
+ },
1447
+ "model.layers.14.mlp.gate_proj": {
1448
+ "bits": 4,
1449
+ "group_size": 64
1450
+ },
1451
+ "model.layers.14.mlp.down_proj": {
1452
+ "bits": 4,
1453
+ "group_size": 64
1454
+ },
1455
+ "model.layers.14.mlp.up_proj": {
1456
+ "bits": 4,
1457
+ "group_size": 64
1458
+ },
1459
+ "model.layers.15.self_attn.q_proj": {
1460
+ "bits": 4,
1461
+ "group_size": 64
1462
+ },
1463
+ "model.layers.15.self_attn.k_proj": {
1464
+ "bits": 4,
1465
+ "group_size": 64
1466
+ },
1467
+ "model.layers.15.self_attn.v_proj": {
1468
+ "bits": 8,
1469
+ "group_size": 64
1470
+ },
1471
+ "model.layers.15.self_attn.o_proj": {
1472
+ "bits": 8,
1473
+ "group_size": 64
1474
+ },
1475
+ "model.layers.15.mlp.gate_proj": {
1476
+ "bits": 4,
1477
+ "group_size": 64
1478
+ },
1479
+ "model.layers.15.mlp.down_proj": {
1480
+ "bits": 4,
1481
+ "group_size": 64
1482
+ },
1483
+ "model.layers.15.mlp.up_proj": {
1484
+ "bits": 8,
1485
+ "group_size": 64
1486
+ },
1487
+ "model.layers.16.self_attn.q_proj": {
1488
+ "bits": 4,
1489
+ "group_size": 64
1490
+ },
1491
+ "model.layers.16.self_attn.k_proj": {
1492
+ "bits": 4,
1493
+ "group_size": 64
1494
+ },
1495
+ "model.layers.16.self_attn.v_proj": {
1496
+ "bits": 8,
1497
+ "group_size": 64
1498
+ },
1499
+ "model.layers.16.self_attn.o_proj": {
1500
+ "bits": 8,
1501
+ "group_size": 64
1502
+ },
1503
+ "model.layers.16.mlp.gate_proj": {
1504
+ "bits": 4,
1505
+ "group_size": 64
1506
+ },
1507
+ "model.layers.16.mlp.down_proj": {
1508
+ "bits": 4,
1509
+ "group_size": 64
1510
+ },
1511
+ "model.layers.16.mlp.up_proj": {
1512
+ "bits": 4,
1513
+ "group_size": 64
1514
+ },
1515
+ "model.layers.17.self_attn.q_proj": {
1516
+ "bits": 4,
1517
+ "group_size": 64
1518
+ },
1519
+ "model.layers.17.self_attn.k_proj": {
1520
+ "bits": 4,
1521
+ "group_size": 64
1522
+ },
1523
+ "model.layers.17.self_attn.v_proj": {
1524
+ "bits": 8,
1525
+ "group_size": 64
1526
+ },
1527
+ "model.layers.17.self_attn.o_proj": {
1528
+ "bits": 8,
1529
+ "group_size": 64
1530
+ },
1531
+ "model.layers.17.mlp.gate_proj": {
1532
+ "bits": 4,
1533
+ "group_size": 64
1534
+ },
1535
+ "model.layers.17.mlp.down_proj": {
1536
+ "bits": 4,
1537
+ "group_size": 64
1538
+ },
1539
+ "model.layers.17.mlp.up_proj": {
1540
+ "bits": 4,
1541
+ "group_size": 64
1542
+ },
1543
+ "model.layers.18.self_attn.q_proj": {
1544
+ "bits": 4,
1545
+ "group_size": 64
1546
+ },
1547
+ "model.layers.18.self_attn.k_proj": {
1548
+ "bits": 4,
1549
+ "group_size": 64
1550
+ },
1551
+ "model.layers.18.self_attn.v_proj": {
1552
+ "bits": 8,
1553
+ "group_size": 64
1554
+ },
1555
+ "model.layers.18.self_attn.o_proj": {
1556
+ "bits": 8,
1557
+ "group_size": 64
1558
+ },
1559
+ "model.layers.18.mlp.gate_proj": {
1560
+ "bits": 4,
1561
+ "group_size": 64
1562
+ },
1563
+ "model.layers.18.mlp.down_proj": {
1564
+ "bits": 4,
1565
+ "group_size": 64
1566
+ },
1567
+ "model.layers.18.mlp.up_proj": {
1568
+ "bits": 8,
1569
+ "group_size": 64
1570
+ },
1571
+ "model.layers.19.self_attn.q_proj": {
1572
+ "bits": 8,
1573
+ "group_size": 64
1574
+ },
1575
+ "model.layers.19.self_attn.k_proj": {
1576
+ "bits": 4,
1577
+ "group_size": 64
1578
+ },
1579
+ "model.layers.19.self_attn.v_proj": {
1580
+ "bits": 8,
1581
+ "group_size": 64
1582
+ },
1583
+ "model.layers.19.self_attn.o_proj": {
1584
+ "bits": 4,
1585
+ "group_size": 64
1586
+ },
1587
+ "model.layers.19.mlp.gate_proj": {
1588
+ "bits": 4,
1589
+ "group_size": 64
1590
+ },
1591
+ "model.layers.19.mlp.down_proj": {
1592
+ "bits": 4,
1593
+ "group_size": 64
1594
+ },
1595
+ "model.layers.19.mlp.up_proj": {
1596
+ "bits": 4,
1597
+ "group_size": 64
1598
+ },
1599
+ "model.layers.20.self_attn.q_proj": {
1600
+ "bits": 4,
1601
+ "group_size": 64
1602
+ },
1603
+ "model.layers.20.self_attn.k_proj": {
1604
+ "bits": 4,
1605
+ "group_size": 64
1606
+ },
1607
+ "model.layers.20.self_attn.v_proj": {
1608
+ "bits": 8,
1609
+ "group_size": 64
1610
+ },
1611
+ "model.layers.20.self_attn.o_proj": {
1612
+ "bits": 8,
1613
+ "group_size": 64
1614
+ },
1615
+ "model.layers.20.mlp.gate_proj": {
1616
+ "bits": 4,
1617
+ "group_size": 64
1618
+ },
1619
+ "model.layers.20.mlp.down_proj": {
1620
+ "bits": 4,
1621
+ "group_size": 64
1622
+ },
1623
+ "model.layers.20.mlp.up_proj": {
1624
+ "bits": 4,
1625
+ "group_size": 64
1626
+ },
1627
+ "model.layers.21.self_attn.q_proj": {
1628
+ "bits": 8,
1629
+ "group_size": 64
1630
+ },
1631
+ "model.layers.21.self_attn.k_proj": {
1632
+ "bits": 4,
1633
+ "group_size": 64
1634
+ },
1635
+ "model.layers.21.self_attn.v_proj": {
1636
+ "bits": 8,
1637
+ "group_size": 64
1638
+ },
1639
+ "model.layers.21.self_attn.o_proj": {
1640
+ "bits": 4,
1641
+ "group_size": 64
1642
+ },
1643
+ "model.layers.21.mlp.gate_proj": {
1644
+ "bits": 4,
1645
+ "group_size": 64
1646
+ },
1647
+ "model.layers.21.mlp.down_proj": {
1648
+ "bits": 4,
1649
+ "group_size": 64
1650
+ },
1651
+ "model.layers.21.mlp.up_proj": {
1652
+ "bits": 8,
1653
+ "group_size": 64
1654
+ },
1655
+ "model.layers.22.self_attn.q_proj": {
1656
+ "bits": 4,
1657
+ "group_size": 64
1658
+ },
1659
+ "model.layers.22.self_attn.k_proj": {
1660
+ "bits": 4,
1661
+ "group_size": 64
1662
+ },
1663
+ "model.layers.22.self_attn.v_proj": {
1664
+ "bits": 8,
1665
+ "group_size": 64
1666
+ },
1667
+ "model.layers.22.self_attn.o_proj": {
1668
+ "bits": 8,
1669
+ "group_size": 64
1670
+ },
1671
+ "model.layers.22.mlp.gate_proj": {
1672
+ "bits": 4,
1673
+ "group_size": 64
1674
+ },
1675
+ "model.layers.22.mlp.down_proj": {
1676
+ "bits": 4,
1677
+ "group_size": 64
1678
+ },
1679
+ "model.layers.22.mlp.up_proj": {
1680
+ "bits": 4,
1681
+ "group_size": 64
1682
+ },
1683
+ "model.layers.23.self_attn.q_proj": {
1684
+ "bits": 4,
1685
+ "group_size": 64
1686
+ },
1687
+ "model.layers.23.self_attn.k_proj": {
1688
+ "bits": 4,
1689
+ "group_size": 64
1690
+ },
1691
+ "model.layers.23.self_attn.v_proj": {
1692
+ "bits": 8,
1693
+ "group_size": 64
1694
+ },
1695
+ "model.layers.23.self_attn.o_proj": {
1696
+ "bits": 8,
1697
+ "group_size": 64
1698
+ },
1699
+ "model.layers.23.mlp.gate_proj": {
1700
+ "bits": 4,
1701
+ "group_size": 64
1702
+ },
1703
+ "model.layers.23.mlp.down_proj": {
1704
+ "bits": 4,
1705
+ "group_size": 64
1706
+ },
1707
+ "model.layers.23.mlp.up_proj": {
1708
+ "bits": 4,
1709
+ "group_size": 64
1710
+ },
1711
+ "model.layers.24.self_attn.q_proj": {
1712
+ "bits": 4,
1713
+ "group_size": 64
1714
+ },
1715
+ "model.layers.24.self_attn.k_proj": {
1716
+ "bits": 4,
1717
+ "group_size": 64
1718
+ },
1719
+ "model.layers.24.self_attn.v_proj": {
1720
+ "bits": 8,
1721
+ "group_size": 64
1722
+ },
1723
+ "model.layers.24.self_attn.o_proj": {
1724
+ "bits": 8,
1725
+ "group_size": 64
1726
+ },
1727
+ "model.layers.24.mlp.gate_proj": {
1728
+ "bits": 4,
1729
+ "group_size": 64
1730
+ },
1731
+ "model.layers.24.mlp.down_proj": {
1732
+ "bits": 4,
1733
+ "group_size": 64
1734
+ },
1735
+ "model.layers.24.mlp.up_proj": {
1736
+ "bits": 8,
1737
+ "group_size": 64
1738
+ },
1739
+ "model.layers.25.self_attn.q_proj": {
1740
+ "bits": 4,
1741
+ "group_size": 64
1742
+ },
1743
+ "model.layers.25.self_attn.k_proj": {
1744
+ "bits": 8,
1745
+ "group_size": 64
1746
+ },
1747
+ "model.layers.25.self_attn.v_proj": {
1748
+ "bits": 8,
1749
+ "group_size": 64
1750
+ },
1751
+ "model.layers.25.self_attn.o_proj": {
1752
+ "bits": 4,
1753
+ "group_size": 64
1754
+ },
1755
+ "model.layers.25.mlp.gate_proj": {
1756
+ "bits": 4,
1757
+ "group_size": 64
1758
+ },
1759
+ "model.layers.25.mlp.down_proj": {
1760
+ "bits": 4,
1761
+ "group_size": 64
1762
+ },
1763
+ "model.layers.25.mlp.up_proj": {
1764
+ "bits": 4,
1765
+ "group_size": 64
1766
+ },
1767
+ "model.layers.26.self_attn.q_proj": {
1768
+ "bits": 4,
1769
+ "group_size": 64
1770
+ },
1771
+ "model.layers.26.self_attn.k_proj": {
1772
+ "bits": 8,
1773
+ "group_size": 64
1774
+ },
1775
+ "model.layers.26.self_attn.v_proj": {
1776
+ "bits": 8,
1777
+ "group_size": 64
1778
+ },
1779
+ "model.layers.26.self_attn.o_proj": {
1780
+ "bits": 4,
1781
+ "group_size": 64
1782
+ },
1783
+ "model.layers.26.mlp.gate_proj": {
1784
+ "bits": 4,
1785
+ "group_size": 64
1786
+ },
1787
+ "model.layers.26.mlp.down_proj": {
1788
+ "bits": 4,
1789
+ "group_size": 64
1790
+ },
1791
+ "model.layers.26.mlp.up_proj": {
1792
+ "bits": 4,
1793
+ "group_size": 64
1794
+ },
1795
+ "model.layers.27.self_attn.q_proj": {
1796
+ "bits": 4,
1797
+ "group_size": 64
1798
+ },
1799
+ "model.layers.27.self_attn.k_proj": {
1800
+ "bits": 8,
1801
+ "group_size": 64
1802
+ },
1803
+ "model.layers.27.self_attn.v_proj": {
1804
+ "bits": 8,
1805
+ "group_size": 64
1806
+ },
1807
+ "model.layers.27.self_attn.o_proj": {
1808
+ "bits": 4,
1809
+ "group_size": 64
1810
+ },
1811
+ "model.layers.27.mlp.gate_proj": {
1812
+ "bits": 4,
1813
+ "group_size": 64
1814
+ },
1815
+ "model.layers.27.mlp.down_proj": {
1816
+ "bits": 8,
1817
+ "group_size": 64
1818
+ },
1819
+ "model.layers.27.mlp.up_proj": {
1820
+ "bits": 4,
1821
+ "group_size": 64
1822
+ },
1823
+ "model.layers.28.self_attn.q_proj": {
1824
+ "bits": 8,
1825
+ "group_size": 64
1826
+ },
1827
+ "model.layers.28.self_attn.k_proj": {
1828
+ "bits": 8,
1829
+ "group_size": 64
1830
+ },
1831
+ "model.layers.28.self_attn.v_proj": {
1832
+ "bits": 4,
1833
+ "group_size": 64
1834
+ },
1835
+ "model.layers.28.self_attn.o_proj": {
1836
+ "bits": 4,
1837
+ "group_size": 64
1838
+ },
1839
+ "model.layers.28.mlp.gate_proj": {
1840
+ "bits": 4,
1841
+ "group_size": 64
1842
+ },
1843
+ "model.layers.28.mlp.down_proj": {
1844
+ "bits": 4,
1845
+ "group_size": 64
1846
+ },
1847
+ "model.layers.28.mlp.up_proj": {
1848
+ "bits": 4,
1849
+ "group_size": 64
1850
+ },
1851
+ "model.layers.29.self_attn.q_proj": {
1852
+ "bits": 4,
1853
+ "group_size": 64
1854
+ },
1855
+ "model.layers.29.self_attn.k_proj": {
1856
+ "bits": 8,
1857
+ "group_size": 64
1858
+ },
1859
+ "model.layers.29.self_attn.v_proj": {
1860
+ "bits": 8,
1861
+ "group_size": 64
1862
+ },
1863
+ "model.layers.29.self_attn.o_proj": {
1864
+ "bits": 4,
1865
+ "group_size": 64
1866
+ },
1867
+ "model.layers.29.mlp.gate_proj": {
1868
+ "bits": 4,
1869
+ "group_size": 64
1870
+ },
1871
+ "model.layers.29.mlp.down_proj": {
1872
+ "bits": 4,
1873
+ "group_size": 64
1874
+ },
1875
+ "model.layers.29.mlp.up_proj": {
1876
+ "bits": 4,
1877
+ "group_size": 64
1878
+ },
1879
+ "model.layers.30.self_attn.q_proj": {
1880
+ "bits": 4,
1881
+ "group_size": 64
1882
+ },
1883
+ "model.layers.30.self_attn.k_proj": {
1884
+ "bits": 8,
1885
+ "group_size": 64
1886
+ },
1887
+ "model.layers.30.self_attn.v_proj": {
1888
+ "bits": 8,
1889
+ "group_size": 64
1890
+ },
1891
+ "model.layers.30.self_attn.o_proj": {
1892
+ "bits": 4,
1893
+ "group_size": 64
1894
+ },
1895
+ "model.layers.30.mlp.gate_proj": {
1896
+ "bits": 8,
1897
+ "group_size": 64
1898
+ },
1899
+ "model.layers.30.mlp.down_proj": {
1900
+ "bits": 4,
1901
+ "group_size": 64
1902
+ },
1903
+ "model.layers.30.mlp.up_proj": {
1904
+ "bits": 4,
1905
+ "group_size": 64
1906
+ },
1907
+ "model.layers.31.self_attn.q_proj": {
1908
+ "bits": 4,
1909
+ "group_size": 64
1910
+ },
1911
+ "model.layers.31.self_attn.k_proj": {
1912
+ "bits": 8,
1913
+ "group_size": 64
1914
+ },
1915
+ "model.layers.31.self_attn.v_proj": {
1916
+ "bits": 8,
1917
+ "group_size": 64
1918
+ },
1919
+ "model.layers.31.self_attn.o_proj": {
1920
+ "bits": 4,
1921
+ "group_size": 64
1922
+ },
1923
+ "model.layers.31.mlp.gate_proj": {
1924
+ "bits": 4,
1925
+ "group_size": 64
1926
+ },
1927
+ "model.layers.31.mlp.down_proj": {
1928
+ "bits": 4,
1929
+ "group_size": 64
1930
+ },
1931
+ "model.layers.31.mlp.up_proj": {
1932
+ "bits": 4,
1933
+ "group_size": 64
1934
+ },
1935
+ "model.layers.32.self_attn.q_proj": {
1936
+ "bits": 8,
1937
+ "group_size": 64
1938
+ },
1939
+ "model.layers.32.self_attn.k_proj": {
1940
+ "bits": 8,
1941
+ "group_size": 64
1942
+ },
1943
+ "model.layers.32.self_attn.v_proj": {
1944
+ "bits": 4,
1945
+ "group_size": 64
1946
+ },
1947
+ "model.layers.32.self_attn.o_proj": {
1948
+ "bits": 4,
1949
+ "group_size": 64
1950
+ },
1951
+ "model.layers.32.mlp.gate_proj": {
1952
+ "bits": 4,
1953
+ "group_size": 64
1954
+ },
1955
+ "model.layers.32.mlp.down_proj": {
1956
+ "bits": 4,
1957
+ "group_size": 64
1958
+ },
1959
+ "model.layers.32.mlp.up_proj": {
1960
+ "bits": 4,
1961
+ "group_size": 64
1962
+ },
1963
+ "model.layers.33.self_attn.q_proj": {
1964
+ "bits": 4,
1965
+ "group_size": 64
1966
+ },
1967
+ "model.layers.33.self_attn.k_proj": {
1968
+ "bits": 8,
1969
+ "group_size": 64
1970
+ },
1971
+ "model.layers.33.self_attn.v_proj": {
1972
+ "bits": 8,
1973
+ "group_size": 64
1974
+ },
1975
+ "model.layers.33.self_attn.o_proj": {
1976
+ "bits": 4,
1977
+ "group_size": 64
1978
+ },
1979
+ "model.layers.33.mlp.gate_proj": {
1980
+ "bits": 4,
1981
+ "group_size": 64
1982
+ },
1983
+ "model.layers.33.mlp.down_proj": {
1984
+ "bits": 4,
1985
+ "group_size": 64
1986
+ },
1987
+ "model.layers.33.mlp.up_proj": {
1988
+ "bits": 8,
1989
+ "group_size": 64
1990
+ },
1991
+ "model.layers.34.self_attn.q_proj": {
1992
+ "bits": 8,
1993
+ "group_size": 64
1994
+ },
1995
+ "model.layers.34.self_attn.k_proj": {
1996
+ "bits": 4,
1997
+ "group_size": 64
1998
+ },
1999
+ "model.layers.34.self_attn.v_proj": {
2000
+ "bits": 8,
2001
+ "group_size": 64
2002
+ },
2003
+ "model.layers.34.self_attn.o_proj": {
2004
+ "bits": 4,
2005
+ "group_size": 64
2006
+ },
2007
+ "model.layers.34.mlp.gate_proj": {
2008
+ "bits": 4,
2009
+ "group_size": 64
2010
+ },
2011
+ "model.layers.34.mlp.down_proj": {
2012
+ "bits": 4,
2013
+ "group_size": 64
2014
+ },
2015
+ "model.layers.34.mlp.up_proj": {
2016
+ "bits": 4,
2017
+ "group_size": 64
2018
+ },
2019
+ "model.layers.35.self_attn.q_proj": {
2020
+ "bits": 4,
2021
+ "group_size": 64
2022
+ },
2023
+ "model.layers.35.self_attn.k_proj": {
2024
+ "bits": 8,
2025
+ "group_size": 64
2026
+ },
2027
+ "model.layers.35.self_attn.v_proj": {
2028
+ "bits": 8,
2029
+ "group_size": 64
2030
+ },
2031
+ "model.layers.35.self_attn.o_proj": {
2032
+ "bits": 8,
2033
+ "group_size": 64
2034
+ },
2035
+ "model.layers.35.mlp.gate_proj": {
2036
+ "bits": 8,
2037
+ "group_size": 64
2038
+ },
2039
+ "model.layers.35.mlp.down_proj": {
2040
+ "bits": 8,
2041
+ "group_size": 64
2042
+ },
2043
+ "model.layers.35.mlp.up_proj": {
2044
+ "bits": 8,
2045
+ "group_size": 64
2046
+ },
2047
+ "lm_head": {
2048
+ "bits": 8,
2049
+ "group_size": 64
2050
+ }
2051
+ },
2052
+ "text_config": {
2053
+ "_name_or_path": "/mage-vl/pretrain_models/Qwen3-4B-Instruct-2507",
2054
+ "architectures": [
2055
+ "MageVLForConditionalGeneration"
2056
+ ],
2057
+ "attention_bias": false,
2058
+ "attention_dropout": 0.0,
2059
+ "bos_token_id": 151643,
2060
+ "dtype": "bfloat16",
2061
+ "eos_token_id": 151645,
2062
+ "head_dim": 128,
2063
+ "hidden_act": "silu",
2064
+ "hidden_size": 2560,
2065
+ "initializer_range": 0.02,
2066
+ "intermediate_size": 9728,
2067
+ "layer_types": [
2068
+ "full_attention",
2069
+ "full_attention",
2070
+ "full_attention",
2071
+ "full_attention",
2072
+ "full_attention",
2073
+ "full_attention",
2074
+ "full_attention",
2075
+ "full_attention",
2076
+ "full_attention",
2077
+ "full_attention",
2078
+ "full_attention",
2079
+ "full_attention",
2080
+ "full_attention",
2081
+ "full_attention",
2082
+ "full_attention",
2083
+ "full_attention",
2084
+ "full_attention",
2085
+ "full_attention",
2086
+ "full_attention",
2087
+ "full_attention",
2088
+ "full_attention",
2089
+ "full_attention",
2090
+ "full_attention",
2091
+ "full_attention",
2092
+ "full_attention",
2093
+ "full_attention",
2094
+ "full_attention",
2095
+ "full_attention",
2096
+ "full_attention",
2097
+ "full_attention",
2098
+ "full_attention",
2099
+ "full_attention",
2100
+ "full_attention",
2101
+ "full_attention",
2102
+ "full_attention",
2103
+ "full_attention"
2104
+ ],
2105
+ "max_position_embeddings": 262144,
2106
+ "max_window_layers": 36,
2107
+ "model_type": "qwen3",
2108
+ "num_attention_heads": 32,
2109
+ "num_hidden_layers": 36,
2110
+ "num_key_value_heads": 8,
2111
+ "rms_norm_eps": 1e-06,
2112
+ "rope_scaling": null,
2113
+ "sliding_window": null,
2114
+ "use_cache": true,
2115
+ "use_sliding_window": false,
2116
+ "vocab_size": 151936,
2117
+ "rope_parameters": {
2118
+ "rope_theta": 5000000,
2119
+ "rope_type": "default"
2120
+ },
2121
+ "tie_word_embeddings": false
2122
+ },
2123
+ "tie_word_embeddings": false,
2124
+ "transformers_version": "5.7.0",
2125
+ "video_token_id": 151656,
2126
+ "vision_end_token_id": 151653,
2127
+ "vision_start_token_id": 151652,
2128
+ "vision_config": {
2129
+ "attention_dropout": 0.0,
2130
+ "frame_windows_size": 4,
2131
+ "hidden_act": "gelu",
2132
+ "hidden_size": 1024,
2133
+ "image_size": 448,
2134
+ "initializer_range": 0.02,
2135
+ "intermediate_size": 4096,
2136
+ "layer_norm_eps": 1e-06,
2137
+ "layer_norm_type": "layer_norm",
2138
+ "model_type": "mage_vl_vision",
2139
+ "num_attention_heads": 16,
2140
+ "num_channels": 3,
2141
+ "num_hidden_layers": 24,
2142
+ "out_hidden_size": 2560,
2143
+ "patch_size": 16,
2144
+ "rope_theta": 10000.0,
2145
+ "spatial_merge_size": 2,
2146
+ "temporal_patch_size": 1,
2147
+ "text_hidden_size": 2560,
2148
+ "tokens_per_second": 1,
2149
+ "use_head": false,
2150
+ "max_position_embeddings": 8192
2151
+ },
2152
+ "optiq_vision": {
2153
+ "sidecar": "optiq/optiq_vision.safetensors",
2154
+ "dtype": "bfloat16",
2155
+ "n_tensors": 297,
2156
+ "base_model": "microsoft/Mage-VL"
2157
+ }
2158
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.57.3"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d46a643f76f2ccd733db5065e220e3d0b31bcc1617cf67d1fb985df7d9ccaf1
3
+ size 3255463645
model.safetensors.index.json ADDED
@@ -0,0 +1,1212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 3255360512,
4
+ "total_parameters": 4411424256
5
+ },
6
+ "weight_map": {
7
+ "lm_head.biases": "model.safetensors",
8
+ "lm_head.scales": "model.safetensors",
9
+ "lm_head.weight": "model.safetensors",
10
+ "model.embed_tokens.biases": "model.safetensors",
11
+ "model.embed_tokens.scales": "model.safetensors",
12
+ "model.embed_tokens.weight": "model.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
14
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
15
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
17
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
18
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
19
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
20
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
21
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
22
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
23
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
24
+ "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
25
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
26
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
27
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
28
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
29
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
30
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
31
+ "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
32
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
33
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
34
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
35
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
36
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
37
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
38
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
39
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
40
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
41
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
42
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
43
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
44
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
45
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
46
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
47
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
48
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
49
+ "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
50
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
51
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
52
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
53
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
54
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
55
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
56
+ "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
57
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
58
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
59
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
60
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
61
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
62
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
63
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
64
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
65
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
66
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
67
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
68
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
69
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
70
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
71
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
72
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
73
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
74
+ "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
75
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
76
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
77
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
78
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
79
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
80
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
81
+ "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
82
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
83
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
84
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
85
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
86
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
87
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
88
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
89
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
90
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
91
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
92
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
93
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
94
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
95
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
96
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
97
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
98
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
99
+ "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
100
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
101
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
102
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
103
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
104
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
105
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
106
+ "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
107
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
108
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
109
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
110
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
111
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
112
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
113
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
114
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
115
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
116
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
117
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
118
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
119
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
120
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
121
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
122
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
123
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
124
+ "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
125
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
126
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
127
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
128
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
129
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
130
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
131
+ "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
132
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
133
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
134
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
135
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
136
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
137
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
138
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
139
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
140
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
141
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
142
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
143
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
144
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
145
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
146
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
147
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
148
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
149
+ "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
150
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
151
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
152
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
153
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
154
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
155
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
156
+ "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
157
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
158
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
159
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
160
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
161
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
162
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
163
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
164
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
165
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
166
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
167
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
168
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
169
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
170
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
171
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
172
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
173
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
174
+ "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
175
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
176
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
177
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
178
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
179
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
180
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
181
+ "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
182
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
183
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
184
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
185
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
186
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
187
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
188
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
189
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
190
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
191
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
192
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
193
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
194
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
195
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
196
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
197
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
198
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
199
+ "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
200
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
201
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
202
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
203
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
204
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
205
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
206
+ "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
207
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
208
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
209
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
210
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
211
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
212
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
213
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
214
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
215
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
216
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
217
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
218
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
219
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
220
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
221
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
222
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
223
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
224
+ "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
225
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
226
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
227
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
228
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
229
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
230
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
231
+ "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
232
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
233
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
234
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
235
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
236
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
237
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
238
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
239
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
240
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
241
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
242
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
243
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
244
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
245
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
246
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
247
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
248
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
249
+ "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
250
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
251
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
252
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
253
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
254
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
255
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
256
+ "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
257
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
258
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
259
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
260
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
261
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
262
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
263
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
264
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
265
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
266
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
267
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
268
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
269
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
270
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
271
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
272
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
273
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
274
+ "model.layers.18.self_attn.k_norm.weight": "model.safetensors",
275
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
276
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
277
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
278
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
279
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
280
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
281
+ "model.layers.18.self_attn.q_norm.weight": "model.safetensors",
282
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
283
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
284
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
285
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
286
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
287
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
288
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
289
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
290
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
291
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
292
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
293
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
294
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
295
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
296
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
297
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
298
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
299
+ "model.layers.19.self_attn.k_norm.weight": "model.safetensors",
300
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
301
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
302
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
303
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
304
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
305
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
306
+ "model.layers.19.self_attn.q_norm.weight": "model.safetensors",
307
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
308
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
309
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
310
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
311
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
312
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
313
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
314
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
315
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
316
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
317
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
318
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
319
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
320
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
321
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
322
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
323
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
324
+ "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
325
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
326
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
327
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
328
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
329
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
330
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
331
+ "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
332
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
333
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
334
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
335
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
336
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
337
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
338
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
339
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
340
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
341
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
342
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
343
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
344
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
345
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
346
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
347
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
348
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
349
+ "model.layers.20.self_attn.k_norm.weight": "model.safetensors",
350
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
351
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
352
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
353
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
354
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
355
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
356
+ "model.layers.20.self_attn.q_norm.weight": "model.safetensors",
357
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
358
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
359
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
360
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
361
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
362
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
363
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
364
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
365
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
366
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
367
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
368
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
369
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
370
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
371
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
372
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
373
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
374
+ "model.layers.21.self_attn.k_norm.weight": "model.safetensors",
375
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
376
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
377
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
378
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
379
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
380
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
381
+ "model.layers.21.self_attn.q_norm.weight": "model.safetensors",
382
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
383
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
384
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
385
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
386
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
387
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
388
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
389
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
390
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
391
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
392
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
393
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
394
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
395
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
396
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
397
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
398
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
399
+ "model.layers.22.self_attn.k_norm.weight": "model.safetensors",
400
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
401
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
402
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
403
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
404
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
405
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
406
+ "model.layers.22.self_attn.q_norm.weight": "model.safetensors",
407
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
408
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
409
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
410
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
411
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
412
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
413
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
414
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
415
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
416
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
417
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
418
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
419
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
420
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
421
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
422
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
423
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
424
+ "model.layers.23.self_attn.k_norm.weight": "model.safetensors",
425
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
426
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
427
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
428
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
429
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
430
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
431
+ "model.layers.23.self_attn.q_norm.weight": "model.safetensors",
432
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
433
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
434
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
435
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
436
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
437
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
438
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
439
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
440
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
441
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
442
+ "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
443
+ "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
444
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
445
+ "model.layers.24.mlp.up_proj.biases": "model.safetensors",
446
+ "model.layers.24.mlp.up_proj.scales": "model.safetensors",
447
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
448
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
449
+ "model.layers.24.self_attn.k_norm.weight": "model.safetensors",
450
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
451
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
452
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
453
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
454
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
455
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
456
+ "model.layers.24.self_attn.q_norm.weight": "model.safetensors",
457
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
458
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
459
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
460
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
461
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
462
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
463
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
464
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
465
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
466
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
467
+ "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
468
+ "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
469
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
470
+ "model.layers.25.mlp.up_proj.biases": "model.safetensors",
471
+ "model.layers.25.mlp.up_proj.scales": "model.safetensors",
472
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
473
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
474
+ "model.layers.25.self_attn.k_norm.weight": "model.safetensors",
475
+ "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
476
+ "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
477
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
478
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
479
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
480
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
481
+ "model.layers.25.self_attn.q_norm.weight": "model.safetensors",
482
+ "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
483
+ "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
484
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
485
+ "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
486
+ "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
487
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
488
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
489
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
490
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
491
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
492
+ "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
493
+ "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
494
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
495
+ "model.layers.26.mlp.up_proj.biases": "model.safetensors",
496
+ "model.layers.26.mlp.up_proj.scales": "model.safetensors",
497
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
498
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
499
+ "model.layers.26.self_attn.k_norm.weight": "model.safetensors",
500
+ "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
501
+ "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
502
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
503
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
504
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
505
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
506
+ "model.layers.26.self_attn.q_norm.weight": "model.safetensors",
507
+ "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
508
+ "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
509
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
510
+ "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
511
+ "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
512
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
513
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
514
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
515
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
516
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
517
+ "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
518
+ "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
519
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
520
+ "model.layers.27.mlp.up_proj.biases": "model.safetensors",
521
+ "model.layers.27.mlp.up_proj.scales": "model.safetensors",
522
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
523
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
524
+ "model.layers.27.self_attn.k_norm.weight": "model.safetensors",
525
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
526
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
527
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
528
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
529
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
530
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
531
+ "model.layers.27.self_attn.q_norm.weight": "model.safetensors",
532
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
533
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
534
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
535
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
536
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
537
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
538
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
539
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
540
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
541
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
542
+ "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
543
+ "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
544
+ "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
545
+ "model.layers.28.mlp.up_proj.biases": "model.safetensors",
546
+ "model.layers.28.mlp.up_proj.scales": "model.safetensors",
547
+ "model.layers.28.mlp.up_proj.weight": "model.safetensors",
548
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
549
+ "model.layers.28.self_attn.k_norm.weight": "model.safetensors",
550
+ "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
551
+ "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
552
+ "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
553
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
554
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
555
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
556
+ "model.layers.28.self_attn.q_norm.weight": "model.safetensors",
557
+ "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
558
+ "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
559
+ "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
560
+ "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
561
+ "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
562
+ "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
563
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
564
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
565
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
566
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
567
+ "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
568
+ "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
569
+ "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
570
+ "model.layers.29.mlp.up_proj.biases": "model.safetensors",
571
+ "model.layers.29.mlp.up_proj.scales": "model.safetensors",
572
+ "model.layers.29.mlp.up_proj.weight": "model.safetensors",
573
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
574
+ "model.layers.29.self_attn.k_norm.weight": "model.safetensors",
575
+ "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
576
+ "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
577
+ "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
578
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
579
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
580
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
581
+ "model.layers.29.self_attn.q_norm.weight": "model.safetensors",
582
+ "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
583
+ "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
584
+ "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
585
+ "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
586
+ "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
587
+ "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
588
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
589
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
590
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
591
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
592
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
593
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
594
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
595
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
596
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
597
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
598
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
599
+ "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
600
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
601
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
602
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
603
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
604
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
605
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
606
+ "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
607
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
608
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
609
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
610
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
611
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
612
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
613
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
614
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
615
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
616
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
617
+ "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
618
+ "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
619
+ "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
620
+ "model.layers.30.mlp.up_proj.biases": "model.safetensors",
621
+ "model.layers.30.mlp.up_proj.scales": "model.safetensors",
622
+ "model.layers.30.mlp.up_proj.weight": "model.safetensors",
623
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
624
+ "model.layers.30.self_attn.k_norm.weight": "model.safetensors",
625
+ "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
626
+ "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
627
+ "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
628
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
629
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
630
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
631
+ "model.layers.30.self_attn.q_norm.weight": "model.safetensors",
632
+ "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
633
+ "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
634
+ "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
635
+ "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
636
+ "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
637
+ "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
638
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
639
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
640
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
641
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
642
+ "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
643
+ "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
644
+ "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
645
+ "model.layers.31.mlp.up_proj.biases": "model.safetensors",
646
+ "model.layers.31.mlp.up_proj.scales": "model.safetensors",
647
+ "model.layers.31.mlp.up_proj.weight": "model.safetensors",
648
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
649
+ "model.layers.31.self_attn.k_norm.weight": "model.safetensors",
650
+ "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
651
+ "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
652
+ "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
653
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
654
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
655
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
656
+ "model.layers.31.self_attn.q_norm.weight": "model.safetensors",
657
+ "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
658
+ "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
659
+ "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
660
+ "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
661
+ "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
662
+ "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
663
+ "model.layers.32.input_layernorm.weight": "model.safetensors",
664
+ "model.layers.32.mlp.down_proj.biases": "model.safetensors",
665
+ "model.layers.32.mlp.down_proj.scales": "model.safetensors",
666
+ "model.layers.32.mlp.down_proj.weight": "model.safetensors",
667
+ "model.layers.32.mlp.gate_proj.biases": "model.safetensors",
668
+ "model.layers.32.mlp.gate_proj.scales": "model.safetensors",
669
+ "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
670
+ "model.layers.32.mlp.up_proj.biases": "model.safetensors",
671
+ "model.layers.32.mlp.up_proj.scales": "model.safetensors",
672
+ "model.layers.32.mlp.up_proj.weight": "model.safetensors",
673
+ "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
674
+ "model.layers.32.self_attn.k_norm.weight": "model.safetensors",
675
+ "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
676
+ "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
677
+ "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
678
+ "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
679
+ "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
680
+ "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
681
+ "model.layers.32.self_attn.q_norm.weight": "model.safetensors",
682
+ "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
683
+ "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
684
+ "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
685
+ "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
686
+ "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
687
+ "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
688
+ "model.layers.33.input_layernorm.weight": "model.safetensors",
689
+ "model.layers.33.mlp.down_proj.biases": "model.safetensors",
690
+ "model.layers.33.mlp.down_proj.scales": "model.safetensors",
691
+ "model.layers.33.mlp.down_proj.weight": "model.safetensors",
692
+ "model.layers.33.mlp.gate_proj.biases": "model.safetensors",
693
+ "model.layers.33.mlp.gate_proj.scales": "model.safetensors",
694
+ "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
695
+ "model.layers.33.mlp.up_proj.biases": "model.safetensors",
696
+ "model.layers.33.mlp.up_proj.scales": "model.safetensors",
697
+ "model.layers.33.mlp.up_proj.weight": "model.safetensors",
698
+ "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
699
+ "model.layers.33.self_attn.k_norm.weight": "model.safetensors",
700
+ "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
701
+ "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
702
+ "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
703
+ "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
704
+ "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
705
+ "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
706
+ "model.layers.33.self_attn.q_norm.weight": "model.safetensors",
707
+ "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
708
+ "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
709
+ "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
710
+ "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
711
+ "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
712
+ "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
713
+ "model.layers.34.input_layernorm.weight": "model.safetensors",
714
+ "model.layers.34.mlp.down_proj.biases": "model.safetensors",
715
+ "model.layers.34.mlp.down_proj.scales": "model.safetensors",
716
+ "model.layers.34.mlp.down_proj.weight": "model.safetensors",
717
+ "model.layers.34.mlp.gate_proj.biases": "model.safetensors",
718
+ "model.layers.34.mlp.gate_proj.scales": "model.safetensors",
719
+ "model.layers.34.mlp.gate_proj.weight": "model.safetensors",
720
+ "model.layers.34.mlp.up_proj.biases": "model.safetensors",
721
+ "model.layers.34.mlp.up_proj.scales": "model.safetensors",
722
+ "model.layers.34.mlp.up_proj.weight": "model.safetensors",
723
+ "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
724
+ "model.layers.34.self_attn.k_norm.weight": "model.safetensors",
725
+ "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
726
+ "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
727
+ "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
728
+ "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
729
+ "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
730
+ "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
731
+ "model.layers.34.self_attn.q_norm.weight": "model.safetensors",
732
+ "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
733
+ "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
734
+ "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
735
+ "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
736
+ "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
737
+ "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
738
+ "model.layers.35.input_layernorm.weight": "model.safetensors",
739
+ "model.layers.35.mlp.down_proj.biases": "model.safetensors",
740
+ "model.layers.35.mlp.down_proj.scales": "model.safetensors",
741
+ "model.layers.35.mlp.down_proj.weight": "model.safetensors",
742
+ "model.layers.35.mlp.gate_proj.biases": "model.safetensors",
743
+ "model.layers.35.mlp.gate_proj.scales": "model.safetensors",
744
+ "model.layers.35.mlp.gate_proj.weight": "model.safetensors",
745
+ "model.layers.35.mlp.up_proj.biases": "model.safetensors",
746
+ "model.layers.35.mlp.up_proj.scales": "model.safetensors",
747
+ "model.layers.35.mlp.up_proj.weight": "model.safetensors",
748
+ "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
749
+ "model.layers.35.self_attn.k_norm.weight": "model.safetensors",
750
+ "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
751
+ "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
752
+ "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
753
+ "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
754
+ "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
755
+ "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
756
+ "model.layers.35.self_attn.q_norm.weight": "model.safetensors",
757
+ "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
758
+ "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
759
+ "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
760
+ "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
761
+ "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
762
+ "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
763
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
764
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
765
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
766
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
767
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
768
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
769
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
770
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
771
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
772
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
773
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
774
+ "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
775
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
776
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
777
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
778
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
779
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
780
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
781
+ "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
782
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
783
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
784
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
785
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
786
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
787
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
788
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
789
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
790
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
791
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
792
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
793
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
794
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
795
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
796
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
797
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
798
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
799
+ "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
800
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
801
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
802
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
803
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
804
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
805
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
806
+ "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
807
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
808
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
809
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
810
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
811
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
812
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
813
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
814
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
815
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
816
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
817
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
818
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
819
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
820
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
821
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
822
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
823
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
824
+ "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
825
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
826
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
827
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
828
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
829
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
830
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
831
+ "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
832
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
833
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
834
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
835
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
836
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
837
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
838
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
839
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
840
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
841
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
842
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
843
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
844
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
845
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
846
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
847
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
848
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
849
+ "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
850
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
851
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
852
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
853
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
854
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
855
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
856
+ "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
857
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
858
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
859
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
860
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
861
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
862
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
863
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
864
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
865
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
866
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
867
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
868
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
869
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
870
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
871
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
872
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
873
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
874
+ "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
875
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
876
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
877
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
878
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
879
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
880
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
881
+ "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
882
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
883
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
884
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
885
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
886
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
887
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
888
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
889
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
890
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
891
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
892
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
893
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
894
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
895
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
896
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
897
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
898
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
899
+ "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
900
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
901
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
902
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
903
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
904
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
905
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
906
+ "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
907
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
908
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
909
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
910
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
911
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
912
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
913
+ "model.norm.weight": "model.safetensors",
914
+ "vision_tower.merger.mlp.2.weight": "optiq/optiq_vision.safetensors",
915
+ "vision_tower.merger.mlp.0.bias": "optiq/optiq_vision.safetensors",
916
+ "vision_tower.merger.ln_q.weight": "optiq/optiq_vision.safetensors",
917
+ "vision_tower.merger.ln_q.bias": "optiq/optiq_vision.safetensors",
918
+ "vision_tower.encoder.layers.22.layer_norm2.bias": "optiq/optiq_vision.safetensors",
919
+ "vision_tower.encoder.layers.4.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
920
+ "vision_tower.layernorm_pre.bias": "optiq/optiq_vision.safetensors",
921
+ "vision_tower.encoder.layers.9.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
922
+ "vision_tower.encoder.layers.16.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
923
+ "vision_tower.encoder.layers.9.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
924
+ "vision_tower.encoder.layers.9.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
925
+ "vision_tower.encoder.layers.17.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
926
+ "vision_tower.encoder.layers.9.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
927
+ "vision_tower.encoder.layers.9.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
928
+ "vision_tower.encoder.layers.19.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
929
+ "vision_tower.encoder.layers.9.layer_norm2.weight": "optiq/optiq_vision.safetensors",
930
+ "vision_tower.encoder.layers.9.layer_norm1.weight": "optiq/optiq_vision.safetensors",
931
+ "vision_tower.encoder.layers.9.layer_norm1.bias": "optiq/optiq_vision.safetensors",
932
+ "vision_tower.encoder.layers.8.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
933
+ "vision_tower.encoder.layers.8.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
934
+ "vision_tower.encoder.layers.8.layer_norm1.bias": "optiq/optiq_vision.safetensors",
935
+ "vision_tower.encoder.layers.7.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
936
+ "vision_tower.encoder.layers.1.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
937
+ "vision_tower.encoder.layers.7.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
938
+ "vision_tower.encoder.layers.7.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
939
+ "vision_tower.encoder.layers.7.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
940
+ "vision_tower.encoder.layers.7.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
941
+ "vision_tower.encoder.layers.7.layer_norm2.bias": "optiq/optiq_vision.safetensors",
942
+ "vision_tower.encoder.layers.2.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
943
+ "vision_tower.encoder.layers.6.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
944
+ "vision_tower.encoder.layers.21.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
945
+ "vision_tower.encoder.layers.6.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
946
+ "vision_tower.encoder.layers.6.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
947
+ "vision_tower.encoder.layers.5.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
948
+ "vision_tower.encoder.layers.13.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
949
+ "vision_tower.encoder.layers.5.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
950
+ "vision_tower.encoder.layers.1.layer_norm1.bias": "optiq/optiq_vision.safetensors",
951
+ "vision_tower.encoder.layers.7.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
952
+ "vision_tower.encoder.layers.5.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
953
+ "vision_tower.encoder.layers.5.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
954
+ "vision_tower.encoder.layers.7.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
955
+ "vision_tower.encoder.layers.5.layer_norm1.weight": "optiq/optiq_vision.safetensors",
956
+ "vision_tower.encoder.layers.4.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
957
+ "vision_tower.encoder.layers.18.layer_norm2.weight": "optiq/optiq_vision.safetensors",
958
+ "vision_tower.encoder.layers.4.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
959
+ "vision_tower.encoder.layers.4.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
960
+ "vision_tower.encoder.layers.4.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
961
+ "vision_tower.encoder.layers.10.layer_norm2.weight": "optiq/optiq_vision.safetensors",
962
+ "vision_tower.encoder.layers.4.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
963
+ "vision_tower.encoder.layers.4.layer_norm2.weight": "optiq/optiq_vision.safetensors",
964
+ "vision_tower.encoder.layers.23.layer_norm2.weight": "optiq/optiq_vision.safetensors",
965
+ "vision_tower.encoder.layers.4.layer_norm2.bias": "optiq/optiq_vision.safetensors",
966
+ "vision_tower.encoder.layers.4.layer_norm1.weight": "optiq/optiq_vision.safetensors",
967
+ "vision_tower.encoder.layers.3.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
968
+ "vision_tower.encoder.layers.4.layer_norm1.bias": "optiq/optiq_vision.safetensors",
969
+ "vision_tower.encoder.layers.20.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
970
+ "vision_tower.encoder.layers.3.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
971
+ "vision_tower.encoder.layers.3.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
972
+ "vision_tower.encoder.layers.3.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
973
+ "vision_tower.encoder.layers.3.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
974
+ "vision_tower.encoder.layers.18.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
975
+ "vision_tower.encoder.layers.2.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
976
+ "vision_tower.encoder.layers.3.layer_norm1.weight": "optiq/optiq_vision.safetensors",
977
+ "vision_tower.encoder.layers.3.layer_norm1.bias": "optiq/optiq_vision.safetensors",
978
+ "vision_tower.encoder.layers.23.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
979
+ "vision_tower.encoder.layers.22.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
980
+ "vision_tower.encoder.layers.23.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
981
+ "vision_tower.encoder.layers.22.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
982
+ "vision_tower.encoder.layers.11.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
983
+ "vision_tower.encoder.layers.17.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
984
+ "vision_tower.encoder.layers.23.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
985
+ "vision_tower.encoder.layers.21.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
986
+ "vision_tower.encoder.layers.22.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
987
+ "vision_tower.merger.mlp.2.bias": "optiq/optiq_vision.safetensors",
988
+ "vision_tower.encoder.layers.22.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
989
+ "vision_tower.encoder.layers.22.layer_norm2.weight": "optiq/optiq_vision.safetensors",
990
+ "vision_tower.encoder.layers.3.layer_norm2.bias": "optiq/optiq_vision.safetensors",
991
+ "vision_tower.encoder.layers.21.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
992
+ "vision_tower.merger.mlp.0.weight": "optiq/optiq_vision.safetensors",
993
+ "vision_tower.encoder.layers.21.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
994
+ "vision_tower.encoder.layers.3.layer_norm2.weight": "optiq/optiq_vision.safetensors",
995
+ "vision_tower.encoder.layers.21.layer_norm2.weight": "optiq/optiq_vision.safetensors",
996
+ "vision_tower.encoder.layers.20.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
997
+ "vision_tower.encoder.layers.20.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
998
+ "vision_tower.encoder.layers.20.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
999
+ "vision_tower.encoder.layers.5.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1000
+ "vision_tower.encoder.layers.20.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1001
+ "vision_tower.encoder.layers.20.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1002
+ "vision_tower.encoder.layers.2.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1003
+ "vision_tower.encoder.layers.5.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1004
+ "vision_tower.encoder.layers.22.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1005
+ "vision_tower.encoder.layers.15.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1006
+ "vision_tower.encoder.layers.2.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1007
+ "vision_tower.encoder.layers.7.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1008
+ "vision_tower.encoder.layers.22.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1009
+ "vision_tower.encoder.layers.2.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1010
+ "vision_tower.encoder.layers.2.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1011
+ "vision_tower.encoder.layers.2.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1012
+ "vision_tower.encoder.layers.19.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1013
+ "vision_tower.encoder.layers.10.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1014
+ "vision_tower.encoder.layers.19.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1015
+ "vision_tower.encoder.layers.1.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1016
+ "vision_tower.encoder.layers.19.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1017
+ "vision_tower.encoder.layers.8.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1018
+ "vision_tower.encoder.layers.19.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1019
+ "vision_tower.encoder.layers.19.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1020
+ "vision_tower.encoder.layers.6.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1021
+ "vision_tower.encoder.layers.19.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1022
+ "vision_tower.encoder.layers.13.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1023
+ "vision_tower.encoder.layers.23.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1024
+ "vision_tower.encoder.layers.20.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1025
+ "vision_tower.encoder.layers.19.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1026
+ "vision_tower.encoder.layers.18.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1027
+ "vision_tower.encoder.layers.1.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1028
+ "vision_tower.encoder.layers.5.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1029
+ "vision_tower.encoder.layers.4.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1030
+ "vision_tower.encoder.layers.18.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1031
+ "vision_tower.encoder.layers.18.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1032
+ "vision_tower.encoder.layers.6.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1033
+ "vision_tower.encoder.layers.20.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1034
+ "vision_tower.encoder.layers.18.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1035
+ "vision_tower.encoder.layers.18.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1036
+ "vision_tower.encoder.layers.5.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1037
+ "vision_tower.encoder.layers.18.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1038
+ "vision_tower.encoder.layers.18.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1039
+ "vision_tower.encoder.layers.11.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1040
+ "vision_tower.encoder.layers.6.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1041
+ "vision_tower.encoder.layers.17.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1042
+ "vision_tower.layernorm_pre.weight": "optiq/optiq_vision.safetensors",
1043
+ "vision_tower.encoder.layers.9.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1044
+ "vision_tower.encoder.layers.17.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1045
+ "vision_tower.encoder.layers.6.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1046
+ "vision_tower.encoder.layers.5.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1047
+ "vision_tower.encoder.layers.17.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1048
+ "vision_tower.encoder.layers.12.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1049
+ "vision_tower.encoder.layers.17.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1050
+ "vision_tower.encoder.layers.23.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1051
+ "vision_tower.encoder.layers.17.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1052
+ "vision_tower.encoder.layers.17.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1053
+ "vision_tower.encoder.layers.17.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1054
+ "vision_tower.encoder.layers.16.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1055
+ "vision_tower.encoder.layers.16.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1056
+ "vision_tower.encoder.layers.16.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1057
+ "vision_tower.encoder.layers.3.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1058
+ "vision_tower.encoder.layers.1.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1059
+ "vision_tower.encoder.layers.16.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1060
+ "vision_tower.encoder.layers.15.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1061
+ "vision_tower.encoder.layers.22.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1062
+ "vision_tower.encoder.layers.16.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1063
+ "vision_tower.encoder.layers.16.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1064
+ "vision_tower.encoder.layers.2.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1065
+ "vision_tower.encoder.layers.16.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1066
+ "vision_tower.encoder.layers.16.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1067
+ "vision_tower.encoder.layers.2.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1068
+ "vision_tower.encoder.layers.16.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1069
+ "vision_tower.encoder.layers.15.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1070
+ "vision_tower.encoder.layers.1.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1071
+ "vision_tower.encoder.layers.15.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1072
+ "vision_tower.encoder.layers.13.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1073
+ "vision_tower.encoder.layers.15.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1074
+ "vision_tower.encoder.layers.3.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1075
+ "vision_tower.encoder.layers.11.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1076
+ "vision_tower.encoder.layers.15.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1077
+ "vision_tower.encoder.layers.9.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1078
+ "vision_tower.encoder.layers.15.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1079
+ "vision_tower.encoder.layers.23.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1080
+ "vision_tower.encoder.layers.15.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1081
+ "vision_tower.encoder.layers.23.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1082
+ "vision_tower.encoder.layers.14.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1083
+ "vision_tower.encoder.layers.2.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1084
+ "vision_tower.encoder.layers.14.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1085
+ "vision_tower.encoder.layers.16.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1086
+ "vision_tower.encoder.layers.14.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1087
+ "vision_tower.encoder.layers.14.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1088
+ "vision_tower.encoder.layers.14.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1089
+ "vision_tower.encoder.layers.13.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1090
+ "vision_tower.encoder.layers.10.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1091
+ "vision_tower.encoder.layers.15.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1092
+ "vision_tower.encoder.layers.13.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1093
+ "vision_tower.encoder.layers.0.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1094
+ "vision_tower.encoder.layers.12.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1095
+ "vision_tower.encoder.layers.11.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1096
+ "vision_tower.encoder.layers.13.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1097
+ "vision_tower.encoder.layers.13.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1098
+ "vision_tower.encoder.layers.0.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1099
+ "vision_tower.encoder.layers.9.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1100
+ "vision_tower.encoder.layers.4.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1101
+ "vision_tower.encoder.layers.12.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1102
+ "vision_tower.encoder.layers.12.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1103
+ "vision_tower.encoder.layers.12.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1104
+ "vision_tower.encoder.layers.12.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1105
+ "vision_tower.encoder.layers.12.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1106
+ "vision_tower.encoder.layers.20.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1107
+ "vision_tower.encoder.layers.0.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1108
+ "vision_tower.embeddings.patch_embedding.weight": "optiq/optiq_vision.safetensors",
1109
+ "vision_tower.encoder.layers.12.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1110
+ "vision_tower.encoder.layers.11.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1111
+ "vision_tower.encoder.layers.11.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1112
+ "vision_tower.encoder.layers.11.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1113
+ "vision_tower.encoder.layers.11.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1114
+ "vision_tower.encoder.layers.11.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1115
+ "vision_tower.encoder.layers.8.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1116
+ "vision_tower.encoder.layers.19.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1117
+ "vision_tower.encoder.layers.0.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1118
+ "vision_tower.encoder.layers.10.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1119
+ "vision_tower.encoder.layers.10.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1120
+ "vision_tower.encoder.layers.23.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1121
+ "vision_tower.encoder.layers.10.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1122
+ "vision_tower.encoder.layers.10.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1123
+ "vision_tower.encoder.layers.18.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1124
+ "vision_tower.encoder.layers.10.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1125
+ "vision_tower.encoder.layers.11.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1126
+ "vision_tower.encoder.layers.1.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1127
+ "vision_tower.encoder.layers.1.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1128
+ "vision_tower.encoder.layers.14.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1129
+ "vision_tower.encoder.layers.1.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1130
+ "vision_tower.encoder.layers.1.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1131
+ "vision_tower.encoder.layers.9.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1132
+ "vision_tower.encoder.layers.8.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1133
+ "vision_tower.encoder.layers.0.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1134
+ "vision_tower.encoder.layers.0.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1135
+ "vision_tower.encoder.layers.12.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1136
+ "vision_tower.encoder.layers.14.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1137
+ "vision_tower.encoder.layers.1.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1138
+ "vision_tower.encoder.layers.19.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1139
+ "vision_tower.encoder.layers.0.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1140
+ "vision_tower.encoder.layers.20.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1141
+ "vision_tower.encoder.layers.13.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1142
+ "vision_tower.encoder.layers.0.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1143
+ "vision_tower.encoder.layers.0.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1144
+ "vision_tower.encoder.layers.8.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1145
+ "vision_tower.encoder.layers.12.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1146
+ "vision_tower.encoder.layers.12.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1147
+ "vision_tower.encoder.layers.18.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1148
+ "vision_tower.encoder.layers.6.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1149
+ "vision_tower.encoder.layers.17.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1150
+ "vision_tower.encoder.layers.15.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1151
+ "vision_tower.encoder.layers.21.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1152
+ "vision_tower.encoder.layers.6.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1153
+ "vision_tower.encoder.layers.6.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1154
+ "vision_tower.encoder.layers.14.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1155
+ "vision_tower.encoder.layers.23.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1156
+ "vision_tower.encoder.layers.0.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1157
+ "vision_tower.encoder.layers.3.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1158
+ "vision_tower.encoder.layers.21.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1159
+ "vision_tower.encoder.layers.10.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1160
+ "vision_tower.encoder.layers.6.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1161
+ "vision_tower.encoder.layers.20.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1162
+ "vision_tower.encoder.layers.15.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1163
+ "vision_tower.encoder.layers.16.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1164
+ "vision_tower.encoder.layers.10.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1165
+ "vision_tower.encoder.layers.7.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1166
+ "vision_tower.encoder.layers.8.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1167
+ "vision_tower.encoder.layers.22.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1168
+ "vision_tower.encoder.layers.6.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1169
+ "vision_tower.encoder.layers.1.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1170
+ "vision_tower.encoder.layers.21.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1171
+ "vision_tower.encoder.layers.22.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1172
+ "vision_tower.encoder.layers.14.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1173
+ "vision_tower.encoder.layers.2.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1174
+ "vision_tower.encoder.layers.14.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1175
+ "vision_tower.encoder.layers.5.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1176
+ "vision_tower.encoder.layers.13.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1177
+ "vision_tower.encoder.layers.23.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1178
+ "vision_tower.encoder.layers.21.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1179
+ "vision_tower.encoder.layers.15.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1180
+ "vision_tower.encoder.layers.23.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1181
+ "vision_tower.encoder.layers.13.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1182
+ "vision_tower.encoder.layers.17.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1183
+ "vision_tower.encoder.layers.0.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1184
+ "vision_tower.encoder.layers.7.layer_norm1.bias": "optiq/optiq_vision.safetensors",
1185
+ "vision_tower.encoder.layers.8.self_attn.qkv.bias": "optiq/optiq_vision.safetensors",
1186
+ "vision_tower.encoder.layers.8.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1187
+ "vision_tower.encoder.layers.21.self_attn.qkv.weight": "optiq/optiq_vision.safetensors",
1188
+ "vision_tower.encoder.layers.14.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1189
+ "vision_tower.encoder.layers.5.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1190
+ "vision_tower.encoder.layers.10.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1191
+ "vision_tower.encoder.layers.8.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1192
+ "vision_tower.encoder.layers.19.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1193
+ "vision_tower.encoder.layers.19.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1194
+ "vision_tower.encoder.layers.10.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1195
+ "vision_tower.encoder.layers.18.mlp.fc1.weight": "optiq/optiq_vision.safetensors",
1196
+ "vision_tower.encoder.layers.11.layer_norm1.weight": "optiq/optiq_vision.safetensors",
1197
+ "vision_tower.encoder.layers.20.layer_norm2.weight": "optiq/optiq_vision.safetensors",
1198
+ "vision_tower.encoder.layers.22.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1199
+ "vision_tower.encoder.layers.14.self_attn.proj.bias": "optiq/optiq_vision.safetensors",
1200
+ "vision_tower.encoder.layers.13.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1201
+ "vision_tower.encoder.layers.2.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1202
+ "vision_tower.encoder.layers.21.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1203
+ "vision_tower.encoder.layers.17.mlp.fc2.weight": "optiq/optiq_vision.safetensors",
1204
+ "vision_tower.encoder.layers.8.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1205
+ "vision_tower.encoder.layers.13.mlp.fc2.bias": "optiq/optiq_vision.safetensors",
1206
+ "vision_tower.encoder.layers.7.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1207
+ "vision_tower.encoder.layers.11.mlp.fc1.bias": "optiq/optiq_vision.safetensors",
1208
+ "vision_tower.encoder.layers.12.self_attn.proj.weight": "optiq/optiq_vision.safetensors",
1209
+ "vision_tower.encoder.layers.21.layer_norm2.bias": "optiq/optiq_vision.safetensors",
1210
+ "vision_tower.encoder.layers.0.layer_norm2.weight": "optiq/optiq_vision.safetensors"
1211
+ }
1212
+ }
optiq/optiq_vision.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51410c34df3aa5f6ed361a9966a0e06a199adaad934e68564b13ab86fab38b31
3
+ size 660774713
optiq_metadata.json ADDED
@@ -0,0 +1,1024 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "method": "optiq_mixed_precision",
3
+ "base_model": "microsoft/Mage-VL",
4
+ "reference": "bf16",
5
+ "target_bpw": 4.5,
6
+ "achieved_bpw": 5.1519348268839105,
7
+ "n_high_bits": 89,
8
+ "n_low_bits": 164,
9
+ "threshold": 0.0,
10
+ "per_layer": {
11
+ "lm_head": {
12
+ "bits": 8,
13
+ "group_size": 64
14
+ },
15
+ "model.layers.35.mlp.up_proj": {
16
+ "bits": 8,
17
+ "group_size": 64
18
+ },
19
+ "model.layers.35.mlp.down_proj": {
20
+ "bits": 8,
21
+ "group_size": 64
22
+ },
23
+ "model.layers.35.mlp.gate_proj": {
24
+ "bits": 8,
25
+ "group_size": 64
26
+ },
27
+ "model.layers.35.self_attn.o_proj": {
28
+ "bits": 8,
29
+ "group_size": 64
30
+ },
31
+ "model.layers.35.self_attn.v_proj": {
32
+ "bits": 8,
33
+ "group_size": 64
34
+ },
35
+ "model.layers.35.self_attn.k_proj": {
36
+ "bits": 8,
37
+ "group_size": 64
38
+ },
39
+ "model.layers.35.self_attn.q_proj": {
40
+ "bits": 4,
41
+ "group_size": 64
42
+ },
43
+ "model.layers.34.mlp.up_proj": {
44
+ "bits": 4,
45
+ "group_size": 64
46
+ },
47
+ "model.layers.34.mlp.down_proj": {
48
+ "bits": 4,
49
+ "group_size": 64
50
+ },
51
+ "model.layers.34.mlp.gate_proj": {
52
+ "bits": 4,
53
+ "group_size": 64
54
+ },
55
+ "model.layers.34.self_attn.o_proj": {
56
+ "bits": 4,
57
+ "group_size": 64
58
+ },
59
+ "model.layers.34.self_attn.v_proj": {
60
+ "bits": 8,
61
+ "group_size": 64
62
+ },
63
+ "model.layers.34.self_attn.k_proj": {
64
+ "bits": 4,
65
+ "group_size": 64
66
+ },
67
+ "model.layers.34.self_attn.q_proj": {
68
+ "bits": 8,
69
+ "group_size": 64
70
+ },
71
+ "model.layers.33.mlp.up_proj": {
72
+ "bits": 8,
73
+ "group_size": 64
74
+ },
75
+ "model.layers.33.mlp.down_proj": {
76
+ "bits": 4,
77
+ "group_size": 64
78
+ },
79
+ "model.layers.33.mlp.gate_proj": {
80
+ "bits": 4,
81
+ "group_size": 64
82
+ },
83
+ "model.layers.33.self_attn.o_proj": {
84
+ "bits": 4,
85
+ "group_size": 64
86
+ },
87
+ "model.layers.33.self_attn.v_proj": {
88
+ "bits": 8,
89
+ "group_size": 64
90
+ },
91
+ "model.layers.33.self_attn.k_proj": {
92
+ "bits": 8,
93
+ "group_size": 64
94
+ },
95
+ "model.layers.33.self_attn.q_proj": {
96
+ "bits": 4,
97
+ "group_size": 64
98
+ },
99
+ "model.layers.32.mlp.up_proj": {
100
+ "bits": 4,
101
+ "group_size": 64
102
+ },
103
+ "model.layers.32.mlp.down_proj": {
104
+ "bits": 4,
105
+ "group_size": 64
106
+ },
107
+ "model.layers.32.mlp.gate_proj": {
108
+ "bits": 4,
109
+ "group_size": 64
110
+ },
111
+ "model.layers.32.self_attn.o_proj": {
112
+ "bits": 4,
113
+ "group_size": 64
114
+ },
115
+ "model.layers.32.self_attn.v_proj": {
116
+ "bits": 4,
117
+ "group_size": 64
118
+ },
119
+ "model.layers.32.self_attn.k_proj": {
120
+ "bits": 8,
121
+ "group_size": 64
122
+ },
123
+ "model.layers.32.self_attn.q_proj": {
124
+ "bits": 8,
125
+ "group_size": 64
126
+ },
127
+ "model.layers.31.mlp.up_proj": {
128
+ "bits": 4,
129
+ "group_size": 64
130
+ },
131
+ "model.layers.31.mlp.down_proj": {
132
+ "bits": 4,
133
+ "group_size": 64
134
+ },
135
+ "model.layers.31.mlp.gate_proj": {
136
+ "bits": 4,
137
+ "group_size": 64
138
+ },
139
+ "model.layers.31.self_attn.o_proj": {
140
+ "bits": 4,
141
+ "group_size": 64
142
+ },
143
+ "model.layers.31.self_attn.v_proj": {
144
+ "bits": 8,
145
+ "group_size": 64
146
+ },
147
+ "model.layers.31.self_attn.k_proj": {
148
+ "bits": 8,
149
+ "group_size": 64
150
+ },
151
+ "model.layers.31.self_attn.q_proj": {
152
+ "bits": 4,
153
+ "group_size": 64
154
+ },
155
+ "model.layers.30.mlp.up_proj": {
156
+ "bits": 4,
157
+ "group_size": 64
158
+ },
159
+ "model.layers.30.mlp.down_proj": {
160
+ "bits": 4,
161
+ "group_size": 64
162
+ },
163
+ "model.layers.30.mlp.gate_proj": {
164
+ "bits": 8,
165
+ "group_size": 64
166
+ },
167
+ "model.layers.30.self_attn.o_proj": {
168
+ "bits": 4,
169
+ "group_size": 64
170
+ },
171
+ "model.layers.30.self_attn.v_proj": {
172
+ "bits": 8,
173
+ "group_size": 64
174
+ },
175
+ "model.layers.30.self_attn.k_proj": {
176
+ "bits": 8,
177
+ "group_size": 64
178
+ },
179
+ "model.layers.30.self_attn.q_proj": {
180
+ "bits": 4,
181
+ "group_size": 64
182
+ },
183
+ "model.layers.29.mlp.up_proj": {
184
+ "bits": 4,
185
+ "group_size": 64
186
+ },
187
+ "model.layers.29.mlp.down_proj": {
188
+ "bits": 4,
189
+ "group_size": 64
190
+ },
191
+ "model.layers.29.mlp.gate_proj": {
192
+ "bits": 4,
193
+ "group_size": 64
194
+ },
195
+ "model.layers.29.self_attn.o_proj": {
196
+ "bits": 4,
197
+ "group_size": 64
198
+ },
199
+ "model.layers.29.self_attn.v_proj": {
200
+ "bits": 8,
201
+ "group_size": 64
202
+ },
203
+ "model.layers.29.self_attn.k_proj": {
204
+ "bits": 8,
205
+ "group_size": 64
206
+ },
207
+ "model.layers.29.self_attn.q_proj": {
208
+ "bits": 4,
209
+ "group_size": 64
210
+ },
211
+ "model.layers.28.mlp.up_proj": {
212
+ "bits": 4,
213
+ "group_size": 64
214
+ },
215
+ "model.layers.28.mlp.down_proj": {
216
+ "bits": 4,
217
+ "group_size": 64
218
+ },
219
+ "model.layers.28.mlp.gate_proj": {
220
+ "bits": 4,
221
+ "group_size": 64
222
+ },
223
+ "model.layers.28.self_attn.o_proj": {
224
+ "bits": 4,
225
+ "group_size": 64
226
+ },
227
+ "model.layers.28.self_attn.v_proj": {
228
+ "bits": 4,
229
+ "group_size": 64
230
+ },
231
+ "model.layers.28.self_attn.k_proj": {
232
+ "bits": 8,
233
+ "group_size": 64
234
+ },
235
+ "model.layers.28.self_attn.q_proj": {
236
+ "bits": 8,
237
+ "group_size": 64
238
+ },
239
+ "model.layers.27.mlp.up_proj": {
240
+ "bits": 4,
241
+ "group_size": 64
242
+ },
243
+ "model.layers.27.mlp.down_proj": {
244
+ "bits": 8,
245
+ "group_size": 64
246
+ },
247
+ "model.layers.27.mlp.gate_proj": {
248
+ "bits": 4,
249
+ "group_size": 64
250
+ },
251
+ "model.layers.27.self_attn.o_proj": {
252
+ "bits": 4,
253
+ "group_size": 64
254
+ },
255
+ "model.layers.27.self_attn.v_proj": {
256
+ "bits": 8,
257
+ "group_size": 64
258
+ },
259
+ "model.layers.27.self_attn.k_proj": {
260
+ "bits": 8,
261
+ "group_size": 64
262
+ },
263
+ "model.layers.27.self_attn.q_proj": {
264
+ "bits": 4,
265
+ "group_size": 64
266
+ },
267
+ "model.layers.26.mlp.up_proj": {
268
+ "bits": 4,
269
+ "group_size": 64
270
+ },
271
+ "model.layers.26.mlp.down_proj": {
272
+ "bits": 4,
273
+ "group_size": 64
274
+ },
275
+ "model.layers.26.mlp.gate_proj": {
276
+ "bits": 4,
277
+ "group_size": 64
278
+ },
279
+ "model.layers.26.self_attn.o_proj": {
280
+ "bits": 4,
281
+ "group_size": 64
282
+ },
283
+ "model.layers.26.self_attn.v_proj": {
284
+ "bits": 8,
285
+ "group_size": 64
286
+ },
287
+ "model.layers.26.self_attn.k_proj": {
288
+ "bits": 8,
289
+ "group_size": 64
290
+ },
291
+ "model.layers.26.self_attn.q_proj": {
292
+ "bits": 4,
293
+ "group_size": 64
294
+ },
295
+ "model.layers.25.mlp.up_proj": {
296
+ "bits": 4,
297
+ "group_size": 64
298
+ },
299
+ "model.layers.25.mlp.down_proj": {
300
+ "bits": 4,
301
+ "group_size": 64
302
+ },
303
+ "model.layers.25.mlp.gate_proj": {
304
+ "bits": 4,
305
+ "group_size": 64
306
+ },
307
+ "model.layers.25.self_attn.o_proj": {
308
+ "bits": 4,
309
+ "group_size": 64
310
+ },
311
+ "model.layers.25.self_attn.v_proj": {
312
+ "bits": 8,
313
+ "group_size": 64
314
+ },
315
+ "model.layers.25.self_attn.k_proj": {
316
+ "bits": 8,
317
+ "group_size": 64
318
+ },
319
+ "model.layers.25.self_attn.q_proj": {
320
+ "bits": 4,
321
+ "group_size": 64
322
+ },
323
+ "model.layers.24.mlp.up_proj": {
324
+ "bits": 8,
325
+ "group_size": 64
326
+ },
327
+ "model.layers.24.mlp.down_proj": {
328
+ "bits": 4,
329
+ "group_size": 64
330
+ },
331
+ "model.layers.24.mlp.gate_proj": {
332
+ "bits": 4,
333
+ "group_size": 64
334
+ },
335
+ "model.layers.24.self_attn.o_proj": {
336
+ "bits": 8,
337
+ "group_size": 64
338
+ },
339
+ "model.layers.24.self_attn.v_proj": {
340
+ "bits": 8,
341
+ "group_size": 64
342
+ },
343
+ "model.layers.24.self_attn.k_proj": {
344
+ "bits": 4,
345
+ "group_size": 64
346
+ },
347
+ "model.layers.24.self_attn.q_proj": {
348
+ "bits": 4,
349
+ "group_size": 64
350
+ },
351
+ "model.layers.23.mlp.up_proj": {
352
+ "bits": 4,
353
+ "group_size": 64
354
+ },
355
+ "model.layers.23.mlp.down_proj": {
356
+ "bits": 4,
357
+ "group_size": 64
358
+ },
359
+ "model.layers.23.mlp.gate_proj": {
360
+ "bits": 4,
361
+ "group_size": 64
362
+ },
363
+ "model.layers.23.self_attn.o_proj": {
364
+ "bits": 8,
365
+ "group_size": 64
366
+ },
367
+ "model.layers.23.self_attn.v_proj": {
368
+ "bits": 8,
369
+ "group_size": 64
370
+ },
371
+ "model.layers.23.self_attn.k_proj": {
372
+ "bits": 4,
373
+ "group_size": 64
374
+ },
375
+ "model.layers.23.self_attn.q_proj": {
376
+ "bits": 4,
377
+ "group_size": 64
378
+ },
379
+ "model.layers.22.mlp.up_proj": {
380
+ "bits": 4,
381
+ "group_size": 64
382
+ },
383
+ "model.layers.22.mlp.down_proj": {
384
+ "bits": 4,
385
+ "group_size": 64
386
+ },
387
+ "model.layers.22.mlp.gate_proj": {
388
+ "bits": 4,
389
+ "group_size": 64
390
+ },
391
+ "model.layers.22.self_attn.o_proj": {
392
+ "bits": 8,
393
+ "group_size": 64
394
+ },
395
+ "model.layers.22.self_attn.v_proj": {
396
+ "bits": 8,
397
+ "group_size": 64
398
+ },
399
+ "model.layers.22.self_attn.k_proj": {
400
+ "bits": 4,
401
+ "group_size": 64
402
+ },
403
+ "model.layers.22.self_attn.q_proj": {
404
+ "bits": 4,
405
+ "group_size": 64
406
+ },
407
+ "model.layers.21.mlp.up_proj": {
408
+ "bits": 8,
409
+ "group_size": 64
410
+ },
411
+ "model.layers.21.mlp.down_proj": {
412
+ "bits": 4,
413
+ "group_size": 64
414
+ },
415
+ "model.layers.21.mlp.gate_proj": {
416
+ "bits": 4,
417
+ "group_size": 64
418
+ },
419
+ "model.layers.21.self_attn.o_proj": {
420
+ "bits": 4,
421
+ "group_size": 64
422
+ },
423
+ "model.layers.21.self_attn.v_proj": {
424
+ "bits": 8,
425
+ "group_size": 64
426
+ },
427
+ "model.layers.21.self_attn.k_proj": {
428
+ "bits": 4,
429
+ "group_size": 64
430
+ },
431
+ "model.layers.21.self_attn.q_proj": {
432
+ "bits": 8,
433
+ "group_size": 64
434
+ },
435
+ "model.layers.20.mlp.up_proj": {
436
+ "bits": 4,
437
+ "group_size": 64
438
+ },
439
+ "model.layers.20.mlp.down_proj": {
440
+ "bits": 4,
441
+ "group_size": 64
442
+ },
443
+ "model.layers.20.mlp.gate_proj": {
444
+ "bits": 4,
445
+ "group_size": 64
446
+ },
447
+ "model.layers.20.self_attn.o_proj": {
448
+ "bits": 8,
449
+ "group_size": 64
450
+ },
451
+ "model.layers.20.self_attn.v_proj": {
452
+ "bits": 8,
453
+ "group_size": 64
454
+ },
455
+ "model.layers.20.self_attn.k_proj": {
456
+ "bits": 4,
457
+ "group_size": 64
458
+ },
459
+ "model.layers.20.self_attn.q_proj": {
460
+ "bits": 4,
461
+ "group_size": 64
462
+ },
463
+ "model.layers.19.mlp.up_proj": {
464
+ "bits": 4,
465
+ "group_size": 64
466
+ },
467
+ "model.layers.19.mlp.down_proj": {
468
+ "bits": 4,
469
+ "group_size": 64
470
+ },
471
+ "model.layers.19.mlp.gate_proj": {
472
+ "bits": 4,
473
+ "group_size": 64
474
+ },
475
+ "model.layers.19.self_attn.o_proj": {
476
+ "bits": 4,
477
+ "group_size": 64
478
+ },
479
+ "model.layers.19.self_attn.v_proj": {
480
+ "bits": 8,
481
+ "group_size": 64
482
+ },
483
+ "model.layers.19.self_attn.k_proj": {
484
+ "bits": 4,
485
+ "group_size": 64
486
+ },
487
+ "model.layers.19.self_attn.q_proj": {
488
+ "bits": 8,
489
+ "group_size": 64
490
+ },
491
+ "model.layers.18.mlp.up_proj": {
492
+ "bits": 8,
493
+ "group_size": 64
494
+ },
495
+ "model.layers.18.mlp.down_proj": {
496
+ "bits": 4,
497
+ "group_size": 64
498
+ },
499
+ "model.layers.18.mlp.gate_proj": {
500
+ "bits": 4,
501
+ "group_size": 64
502
+ },
503
+ "model.layers.18.self_attn.o_proj": {
504
+ "bits": 8,
505
+ "group_size": 64
506
+ },
507
+ "model.layers.18.self_attn.v_proj": {
508
+ "bits": 8,
509
+ "group_size": 64
510
+ },
511
+ "model.layers.18.self_attn.k_proj": {
512
+ "bits": 4,
513
+ "group_size": 64
514
+ },
515
+ "model.layers.18.self_attn.q_proj": {
516
+ "bits": 4,
517
+ "group_size": 64
518
+ },
519
+ "model.layers.17.mlp.up_proj": {
520
+ "bits": 4,
521
+ "group_size": 64
522
+ },
523
+ "model.layers.17.mlp.down_proj": {
524
+ "bits": 4,
525
+ "group_size": 64
526
+ },
527
+ "model.layers.17.mlp.gate_proj": {
528
+ "bits": 4,
529
+ "group_size": 64
530
+ },
531
+ "model.layers.17.self_attn.o_proj": {
532
+ "bits": 8,
533
+ "group_size": 64
534
+ },
535
+ "model.layers.17.self_attn.v_proj": {
536
+ "bits": 8,
537
+ "group_size": 64
538
+ },
539
+ "model.layers.17.self_attn.k_proj": {
540
+ "bits": 4,
541
+ "group_size": 64
542
+ },
543
+ "model.layers.17.self_attn.q_proj": {
544
+ "bits": 4,
545
+ "group_size": 64
546
+ },
547
+ "model.layers.16.mlp.up_proj": {
548
+ "bits": 4,
549
+ "group_size": 64
550
+ },
551
+ "model.layers.16.mlp.down_proj": {
552
+ "bits": 4,
553
+ "group_size": 64
554
+ },
555
+ "model.layers.16.mlp.gate_proj": {
556
+ "bits": 4,
557
+ "group_size": 64
558
+ },
559
+ "model.layers.16.self_attn.o_proj": {
560
+ "bits": 8,
561
+ "group_size": 64
562
+ },
563
+ "model.layers.16.self_attn.v_proj": {
564
+ "bits": 8,
565
+ "group_size": 64
566
+ },
567
+ "model.layers.16.self_attn.k_proj": {
568
+ "bits": 4,
569
+ "group_size": 64
570
+ },
571
+ "model.layers.16.self_attn.q_proj": {
572
+ "bits": 4,
573
+ "group_size": 64
574
+ },
575
+ "model.layers.15.mlp.up_proj": {
576
+ "bits": 8,
577
+ "group_size": 64
578
+ },
579
+ "model.layers.15.mlp.down_proj": {
580
+ "bits": 4,
581
+ "group_size": 64
582
+ },
583
+ "model.layers.15.mlp.gate_proj": {
584
+ "bits": 4,
585
+ "group_size": 64
586
+ },
587
+ "model.layers.15.self_attn.o_proj": {
588
+ "bits": 8,
589
+ "group_size": 64
590
+ },
591
+ "model.layers.15.self_attn.v_proj": {
592
+ "bits": 8,
593
+ "group_size": 64
594
+ },
595
+ "model.layers.15.self_attn.k_proj": {
596
+ "bits": 4,
597
+ "group_size": 64
598
+ },
599
+ "model.layers.15.self_attn.q_proj": {
600
+ "bits": 4,
601
+ "group_size": 64
602
+ },
603
+ "model.layers.14.mlp.up_proj": {
604
+ "bits": 4,
605
+ "group_size": 64
606
+ },
607
+ "model.layers.14.mlp.down_proj": {
608
+ "bits": 4,
609
+ "group_size": 64
610
+ },
611
+ "model.layers.14.mlp.gate_proj": {
612
+ "bits": 4,
613
+ "group_size": 64
614
+ },
615
+ "model.layers.14.self_attn.o_proj": {
616
+ "bits": 4,
617
+ "group_size": 64
618
+ },
619
+ "model.layers.14.self_attn.v_proj": {
620
+ "bits": 8,
621
+ "group_size": 64
622
+ },
623
+ "model.layers.14.self_attn.k_proj": {
624
+ "bits": 4,
625
+ "group_size": 64
626
+ },
627
+ "model.layers.14.self_attn.q_proj": {
628
+ "bits": 8,
629
+ "group_size": 64
630
+ },
631
+ "model.layers.13.mlp.up_proj": {
632
+ "bits": 4,
633
+ "group_size": 64
634
+ },
635
+ "model.layers.13.mlp.down_proj": {
636
+ "bits": 4,
637
+ "group_size": 64
638
+ },
639
+ "model.layers.13.mlp.gate_proj": {
640
+ "bits": 4,
641
+ "group_size": 64
642
+ },
643
+ "model.layers.13.self_attn.o_proj": {
644
+ "bits": 8,
645
+ "group_size": 64
646
+ },
647
+ "model.layers.13.self_attn.v_proj": {
648
+ "bits": 8,
649
+ "group_size": 64
650
+ },
651
+ "model.layers.13.self_attn.k_proj": {
652
+ "bits": 4,
653
+ "group_size": 64
654
+ },
655
+ "model.layers.13.self_attn.q_proj": {
656
+ "bits": 4,
657
+ "group_size": 64
658
+ },
659
+ "model.layers.12.mlp.up_proj": {
660
+ "bits": 4,
661
+ "group_size": 64
662
+ },
663
+ "model.layers.12.mlp.down_proj": {
664
+ "bits": 8,
665
+ "group_size": 64
666
+ },
667
+ "model.layers.12.mlp.gate_proj": {
668
+ "bits": 4,
669
+ "group_size": 64
670
+ },
671
+ "model.layers.12.self_attn.o_proj": {
672
+ "bits": 8,
673
+ "group_size": 64
674
+ },
675
+ "model.layers.12.self_attn.v_proj": {
676
+ "bits": 8,
677
+ "group_size": 64
678
+ },
679
+ "model.layers.12.self_attn.k_proj": {
680
+ "bits": 4,
681
+ "group_size": 64
682
+ },
683
+ "model.layers.12.self_attn.q_proj": {
684
+ "bits": 4,
685
+ "group_size": 64
686
+ },
687
+ "model.layers.11.mlp.up_proj": {
688
+ "bits": 4,
689
+ "group_size": 64
690
+ },
691
+ "model.layers.11.mlp.down_proj": {
692
+ "bits": 4,
693
+ "group_size": 64
694
+ },
695
+ "model.layers.11.mlp.gate_proj": {
696
+ "bits": 4,
697
+ "group_size": 64
698
+ },
699
+ "model.layers.11.self_attn.o_proj": {
700
+ "bits": 8,
701
+ "group_size": 64
702
+ },
703
+ "model.layers.11.self_attn.v_proj": {
704
+ "bits": 8,
705
+ "group_size": 64
706
+ },
707
+ "model.layers.11.self_attn.k_proj": {
708
+ "bits": 4,
709
+ "group_size": 64
710
+ },
711
+ "model.layers.11.self_attn.q_proj": {
712
+ "bits": 4,
713
+ "group_size": 64
714
+ },
715
+ "model.layers.10.mlp.up_proj": {
716
+ "bits": 4,
717
+ "group_size": 64
718
+ },
719
+ "model.layers.10.mlp.down_proj": {
720
+ "bits": 4,
721
+ "group_size": 64
722
+ },
723
+ "model.layers.10.mlp.gate_proj": {
724
+ "bits": 4,
725
+ "group_size": 64
726
+ },
727
+ "model.layers.10.self_attn.o_proj": {
728
+ "bits": 4,
729
+ "group_size": 64
730
+ },
731
+ "model.layers.10.self_attn.v_proj": {
732
+ "bits": 8,
733
+ "group_size": 64
734
+ },
735
+ "model.layers.10.self_attn.k_proj": {
736
+ "bits": 8,
737
+ "group_size": 64
738
+ },
739
+ "model.layers.10.self_attn.q_proj": {
740
+ "bits": 4,
741
+ "group_size": 64
742
+ },
743
+ "model.layers.9.mlp.up_proj": {
744
+ "bits": 4,
745
+ "group_size": 64
746
+ },
747
+ "model.layers.9.mlp.down_proj": {
748
+ "bits": 8,
749
+ "group_size": 64
750
+ },
751
+ "model.layers.9.mlp.gate_proj": {
752
+ "bits": 4,
753
+ "group_size": 64
754
+ },
755
+ "model.layers.9.self_attn.o_proj": {
756
+ "bits": 4,
757
+ "group_size": 64
758
+ },
759
+ "model.layers.9.self_attn.v_proj": {
760
+ "bits": 8,
761
+ "group_size": 64
762
+ },
763
+ "model.layers.9.self_attn.k_proj": {
764
+ "bits": 8,
765
+ "group_size": 64
766
+ },
767
+ "model.layers.9.self_attn.q_proj": {
768
+ "bits": 4,
769
+ "group_size": 64
770
+ },
771
+ "model.layers.8.mlp.up_proj": {
772
+ "bits": 4,
773
+ "group_size": 64
774
+ },
775
+ "model.layers.8.mlp.down_proj": {
776
+ "bits": 4,
777
+ "group_size": 64
778
+ },
779
+ "model.layers.8.mlp.gate_proj": {
780
+ "bits": 4,
781
+ "group_size": 64
782
+ },
783
+ "model.layers.8.self_attn.o_proj": {
784
+ "bits": 8,
785
+ "group_size": 64
786
+ },
787
+ "model.layers.8.self_attn.v_proj": {
788
+ "bits": 8,
789
+ "group_size": 64
790
+ },
791
+ "model.layers.8.self_attn.k_proj": {
792
+ "bits": 4,
793
+ "group_size": 64
794
+ },
795
+ "model.layers.8.self_attn.q_proj": {
796
+ "bits": 4,
797
+ "group_size": 64
798
+ },
799
+ "model.layers.7.mlp.up_proj": {
800
+ "bits": 4,
801
+ "group_size": 64
802
+ },
803
+ "model.layers.7.mlp.down_proj": {
804
+ "bits": 4,
805
+ "group_size": 64
806
+ },
807
+ "model.layers.7.mlp.gate_proj": {
808
+ "bits": 4,
809
+ "group_size": 64
810
+ },
811
+ "model.layers.7.self_attn.o_proj": {
812
+ "bits": 4,
813
+ "group_size": 64
814
+ },
815
+ "model.layers.7.self_attn.v_proj": {
816
+ "bits": 8,
817
+ "group_size": 64
818
+ },
819
+ "model.layers.7.self_attn.k_proj": {
820
+ "bits": 8,
821
+ "group_size": 64
822
+ },
823
+ "model.layers.7.self_attn.q_proj": {
824
+ "bits": 4,
825
+ "group_size": 64
826
+ },
827
+ "model.layers.6.mlp.up_proj": {
828
+ "bits": 4,
829
+ "group_size": 64
830
+ },
831
+ "model.layers.6.mlp.down_proj": {
832
+ "bits": 8,
833
+ "group_size": 64
834
+ },
835
+ "model.layers.6.mlp.gate_proj": {
836
+ "bits": 4,
837
+ "group_size": 64
838
+ },
839
+ "model.layers.6.self_attn.o_proj": {
840
+ "bits": 8,
841
+ "group_size": 64
842
+ },
843
+ "model.layers.6.self_attn.v_proj": {
844
+ "bits": 8,
845
+ "group_size": 64
846
+ },
847
+ "model.layers.6.self_attn.k_proj": {
848
+ "bits": 4,
849
+ "group_size": 64
850
+ },
851
+ "model.layers.6.self_attn.q_proj": {
852
+ "bits": 4,
853
+ "group_size": 64
854
+ },
855
+ "model.layers.5.mlp.up_proj": {
856
+ "bits": 4,
857
+ "group_size": 64
858
+ },
859
+ "model.layers.5.mlp.down_proj": {
860
+ "bits": 4,
861
+ "group_size": 64
862
+ },
863
+ "model.layers.5.mlp.gate_proj": {
864
+ "bits": 4,
865
+ "group_size": 64
866
+ },
867
+ "model.layers.5.self_attn.o_proj": {
868
+ "bits": 8,
869
+ "group_size": 64
870
+ },
871
+ "model.layers.5.self_attn.v_proj": {
872
+ "bits": 8,
873
+ "group_size": 64
874
+ },
875
+ "model.layers.5.self_attn.k_proj": {
876
+ "bits": 4,
877
+ "group_size": 64
878
+ },
879
+ "model.layers.5.self_attn.q_proj": {
880
+ "bits": 4,
881
+ "group_size": 64
882
+ },
883
+ "model.layers.4.mlp.up_proj": {
884
+ "bits": 4,
885
+ "group_size": 64
886
+ },
887
+ "model.layers.4.mlp.down_proj": {
888
+ "bits": 4,
889
+ "group_size": 64
890
+ },
891
+ "model.layers.4.mlp.gate_proj": {
892
+ "bits": 4,
893
+ "group_size": 64
894
+ },
895
+ "model.layers.4.self_attn.o_proj": {
896
+ "bits": 8,
897
+ "group_size": 64
898
+ },
899
+ "model.layers.4.self_attn.v_proj": {
900
+ "bits": 8,
901
+ "group_size": 64
902
+ },
903
+ "model.layers.4.self_attn.k_proj": {
904
+ "bits": 4,
905
+ "group_size": 64
906
+ },
907
+ "model.layers.4.self_attn.q_proj": {
908
+ "bits": 4,
909
+ "group_size": 64
910
+ },
911
+ "model.layers.3.mlp.up_proj": {
912
+ "bits": 4,
913
+ "group_size": 64
914
+ },
915
+ "model.layers.3.mlp.down_proj": {
916
+ "bits": 4,
917
+ "group_size": 64
918
+ },
919
+ "model.layers.3.mlp.gate_proj": {
920
+ "bits": 8,
921
+ "group_size": 64
922
+ },
923
+ "model.layers.3.self_attn.o_proj": {
924
+ "bits": 8,
925
+ "group_size": 64
926
+ },
927
+ "model.layers.3.self_attn.v_proj": {
928
+ "bits": 8,
929
+ "group_size": 64
930
+ },
931
+ "model.layers.3.self_attn.k_proj": {
932
+ "bits": 4,
933
+ "group_size": 64
934
+ },
935
+ "model.layers.3.self_attn.q_proj": {
936
+ "bits": 4,
937
+ "group_size": 64
938
+ },
939
+ "model.layers.2.mlp.up_proj": {
940
+ "bits": 4,
941
+ "group_size": 64
942
+ },
943
+ "model.layers.2.mlp.down_proj": {
944
+ "bits": 4,
945
+ "group_size": 64
946
+ },
947
+ "model.layers.2.mlp.gate_proj": {
948
+ "bits": 4,
949
+ "group_size": 64
950
+ },
951
+ "model.layers.2.self_attn.o_proj": {
952
+ "bits": 4,
953
+ "group_size": 64
954
+ },
955
+ "model.layers.2.self_attn.v_proj": {
956
+ "bits": 8,
957
+ "group_size": 64
958
+ },
959
+ "model.layers.2.self_attn.k_proj": {
960
+ "bits": 4,
961
+ "group_size": 64
962
+ },
963
+ "model.layers.2.self_attn.q_proj": {
964
+ "bits": 8,
965
+ "group_size": 64
966
+ },
967
+ "model.layers.1.mlp.up_proj": {
968
+ "bits": 4,
969
+ "group_size": 64
970
+ },
971
+ "model.layers.1.mlp.down_proj": {
972
+ "bits": 4,
973
+ "group_size": 64
974
+ },
975
+ "model.layers.1.mlp.gate_proj": {
976
+ "bits": 4,
977
+ "group_size": 64
978
+ },
979
+ "model.layers.1.self_attn.o_proj": {
980
+ "bits": 8,
981
+ "group_size": 64
982
+ },
983
+ "model.layers.1.self_attn.v_proj": {
984
+ "bits": 8,
985
+ "group_size": 64
986
+ },
987
+ "model.layers.1.self_attn.k_proj": {
988
+ "bits": 4,
989
+ "group_size": 64
990
+ },
991
+ "model.layers.1.self_attn.q_proj": {
992
+ "bits": 4,
993
+ "group_size": 64
994
+ },
995
+ "model.layers.0.mlp.up_proj": {
996
+ "bits": 4,
997
+ "group_size": 64
998
+ },
999
+ "model.layers.0.mlp.down_proj": {
1000
+ "bits": 8,
1001
+ "group_size": 64
1002
+ },
1003
+ "model.layers.0.mlp.gate_proj": {
1004
+ "bits": 4,
1005
+ "group_size": 64
1006
+ },
1007
+ "model.layers.0.self_attn.o_proj": {
1008
+ "bits": 8,
1009
+ "group_size": 64
1010
+ },
1011
+ "model.layers.0.self_attn.v_proj": {
1012
+ "bits": 8,
1013
+ "group_size": 64
1014
+ },
1015
+ "model.layers.0.self_attn.k_proj": {
1016
+ "bits": 4,
1017
+ "group_size": 64
1018
+ },
1019
+ "model.layers.0.self_attn.q_proj": {
1020
+ "bits": 4,
1021
+ "group_size": 64
1022
+ }
1023
+ }
1024
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7aabe7a3b44651592a99607bb33066e6965260336be9218cccd53af161491d
3
+ size 11422060
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "local_files_only": false,
10
+ "max_length": null,
11
+ "model_max_length": 131072,
12
+ "pad_to_multiple_of": null,
13
+ "pad_token": "<|endoftext|>",
14
+ "pad_token_type_id": 0,
15
+ "padding_side": "right",
16
+ "processor_class": "Qwen2_5_VLProcessor",
17
+ "split_special_tokens": false,
18
+ "tokenizer_class": "Qwen2Tokenizer",
19
+ "unk_token": null,
20
+ "use_fast": true
21
+ }