Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/comfyui_kandinsky5.png filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_10s_vs_kandinsky_5_video_lite_distill_10s.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_5s_vs_kandinsky_5_video_lite_distill_5s.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_sora.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_1.3B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_14B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_5B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_A14B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/vbench.png filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/model_index-checkpoint.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "Kandinsky5T2VPipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2VLProcessor"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Kandinsky5Transformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLHunyuanVideo"
+  ]
+}

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "Kandinsky5T2VPipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2VLProcessor"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Kandinsky5Transformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLHunyuanVideo"
+  ]
+}

scheduler/.ipynb_checkpoints/scheduler_config-checkpoint.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "num_train_timesteps": 1000,
+  "shift": 5.0
+}

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "num_train_timesteps": 1000,
+  "shift": 5.0
+}

text_encoder/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

text_encoder/.ipynb_checkpoints/chat_template-checkpoint.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

text_encoder/.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "intermediate_size": 3420,
+    "num_heads": 16,
+    "in_chans": 3,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "window_size": 112,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "tokens_per_second": 2,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 152064
+}

text_encoder/.ipynb_checkpoints/generation_config-checkpoint.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.37.0"
+}

text_encoder/.ipynb_checkpoints/model.safetensors.index-checkpoint.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00004-of-00005.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00005.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors"
+  }
+}

text_encoder/README.md

@@ -0,0 +1,528 @@
+
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+library_name: transformers
+---
+
+# Qwen2.5-VL-7B-Instruct
+<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+
+## Introduction
+
+In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL.
+
+#### Key Enhancements:
+* **Understand things visually**: Qwen2.5-VL is not only proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
+
+* **Being agentic**: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use.
+
+* **Understanding long videos and capturing events**: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of cpaturing event by pinpointing the relevant video segments.
+
+* **Capable of visual localization in different formats**: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes.
+
+* **Generating structured outputs**: for data like scans of invoices, forms, tables, etc. Qwen2.5-VL supports structured outputs of their contents, benefiting usages in finance, commerce, etc.
+
+
+#### Model Architecture Updates:
+
+* **Dynamic Resolution and Frame Rate Training for Video Understanding**:
+
+We extend dynamic resolution to the temporal dimension by adopting dynamic FPS sampling, enabling the model to comprehend videos at various sampling rates. Accordingly, we update mRoPE in the time dimension with IDs and absolute time alignment, enabling the model to learn temporal sequence and speed, and ultimately acquire the ability to pinpoint specific moments.
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-VL/qwen2.5vl_arc.jpeg" width="80%"/>
+<p>
+
+
+* **Streamlined and Efficient Vision Encoder**
+
+We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM.
+
+
+We have three models with 3, 7 and 72 billion parameters. This repo contains the instruction-tuned 7B Qwen2.5-VL model. For more information, visit our [Blog](https://qwenlm.github.io/blog/qwen2.5-vl/) and [GitHub](https://github.com/QwenLM/Qwen2.5-VL).
+
+
+
+## Evaluation
+
+### Image benchmark
+
+
+| Benchmark | InternVL2.5-8B | MiniCPM-o 2.6 | GPT-4o-mini | Qwen2-VL-7B |**Qwen2.5-VL-7B** |
+| :--- | :---: | :---: | :---: | :---: | :---: |
+| MMMU<sub>val</sub>  | 56 | 50.4 | **60**| 54.1 | 58.6|
+| MMMU-Pro<sub>val</sub>  | 34.3 | - | 37.6| 30.5 | 41.0|
+| DocVQA<sub>test</sub>  | 93 | 93 | - | 94.5 | **95.7** |
+| InfoVQA<sub>test</sub>  | 77.6 | - |  - |76.5 | **82.6** |
+| ChartQA<sub>test</sub>  | 84.8 | - |- | 83.0 |**87.3** |
+| TextVQA<sub>val</sub>  | 79.1 | 80.1 | -| 84.3 | **84.9**|
+| OCRBench | 822 | 852 | 785 | 845 | **864** |
+| CC_OCR | 57.7 |  | | 61.6 | **77.8**|
+| MMStar | 62.8| | |60.7| **63.9**|
+| MMBench-V1.1-En<sub>test</sub>  | 79.4 | 78.0 | 76.0| 80.7 | **82.6** |
+| MMT-Bench<sub>test</sub> | - | - | - |**63.7** |63.6 |
+| MMStar | **61.5** | 57.5 |  54.8 | 60.7 |63.9 |
+| MMVet<sub>GPT-4-Turbo</sub>  | 54.2 | 60.0 | 66.9 | 62.0 | **67.1**|
+| HallBench<sub>avg</sub>  | 45.2 | 48.1 | 46.1| 50.6 | **52.9**|
+| MathVista<sub>testmini</sub>  | 58.3 | 60.6 | 52.4 | 58.2 | **68.2**|
+| MathVision  | - | -  | - | 16.3 | **25.07** |
+
+### Video Benchmarks
+
+| Benchmark |  Qwen2-VL-7B | **Qwen2.5-VL-7B** |
+| :--- | :---: | :---: |
+| MVBench |  67.0 | **69.6** |
+| PerceptionTest<sub>test</sub>  | 66.9 | **70.5** |
+| Video-MME<sub>wo/w subs</sub>   | 63.3/69.0 | **65.1**/**71.6** |
+| LVBench  |  | 45.3 |
+| LongVideoBench  |  | 54.7 |
+| MMBench-Video | 1.44 | 1.79 |
+| TempCompass |  | 71.7 |
+| MLVU |  | 70.2 |
+| CharadesSTA/mIoU |  43.6|
+
+### Agent benchmark
+| Benchmarks              | Qwen2.5-VL-7B |
+|-------------------------|---------------|
+| ScreenSpot              |     84.7    |
+| ScreenSpot Pro          |     29.0    |
+| AITZ_EM                 |  	81.9    |
+| Android Control High_EM |    	60.1    |
+| Android Control Low_EM  |  	93.7    |
+| AndroidWorld_SR         | 	25.5  	|
+| MobileMiniWob++_SR      | 	91.4    |
+
+## Requirements
+The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
+```
+pip install git+https://github.com/huggingface/transformers accelerate
+```
+or you might encounter the following error:
+```
+KeyError: 'qwen2_5_vl'
+```
+
+
+## Quickstart
+
+Below, we provide simple examples to show how to use Qwen2.5-VL with 🤖 ModelScope and 🤗 Transformers.
+
+The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
+```
+pip install git+https://github.com/huggingface/transformers accelerate
+```
+or you might encounter the following error:
+```
+KeyError: 'qwen2_5_vl'
+```
+
+
+We offer a toolkit to help you handle various types of visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved images and videos. You can install it using the following command:
+
+```bash
+# It's highly recommanded to use `[decord]` feature for faster video loading.
+pip install qwen-vl-utils[decord]==0.0.8
+```
+
+If you are not using Linux, you might not be able to install `decord` from PyPI. In that case, you can use `pip install qwen-vl-utils` which will fall back to using torchvision for video processing. However, you can still [install decord from source](https://github.com/dmlc/decord?tab=readme-ov-file#install-from-source) to get decord used when loading video.
+
+### Using 🤗  Transformers to Chat
+
+Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
+
+```python
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+
+# default: Load the model on the available device(s)
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
+)
+
+# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
+# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+#     "Qwen/Qwen2.5-VL-7B-Instruct",
+#     torch_dtype=torch.bfloat16,
+#     attn_implementation="flash_attention_2",
+#     device_map="auto",
+# )
+
+# default processer
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
+
+# The default range for the number of visual tokens per image in the model is 4-16384.
+# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
+# min_pixels = 256*28*28
+# max_pixels = 1280*28*28
+# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+# Inference: Generation of the output
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+<details>
+<summary>Multi image inference</summary>
+
+```python
+# Messages containing multiple images and a text query
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "file:///path/to/image1.jpg"},
+            {"type": "image", "image": "file:///path/to/image2.jpg"},
+            {"type": "text", "text": "Identify the similarities between these images."},
+        ],
+    }
+]
+
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+# Inference
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+</details>
+
+<details>
+<summary>Video inference</summary>
+
+```python
+# Messages containing a images list as a video and a text query
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "video",
+                "video": [
+                    "file:///path/to/frame1.jpg",
+                    "file:///path/to/frame2.jpg",
+                    "file:///path/to/frame3.jpg",
+                    "file:///path/to/frame4.jpg",
+                ],
+            },
+            {"type": "text", "text": "Describe this video."},
+        ],
+    }
+]
+
+# Messages containing a local video path and a text query
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "video",
+                "video": "file:///path/to/video1.mp4",
+                "max_pixels": 360 * 420,
+                "fps": 1.0,
+            },
+            {"type": "text", "text": "Describe this video."},
+        ],
+    }
+]
+
+# Messages containing a video url and a text query
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "video",
+                "video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/space_woaudio.mp4",
+            },
+            {"type": "text", "text": "Describe this video."},
+        ],
+    }
+]
+
+#In Qwen 2.5 VL, frame rate information is also input into the model to align with absolute time.
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    fps=fps,
+    padding=True,
+    return_tensors="pt",
+    **video_kwargs,
+)
+inputs = inputs.to("cuda")
+
+# Inference
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```
+
+Video URL compatibility largely depends on the third-party library version. The details are in the table below. change the backend by `FORCE_QWENVL_VIDEO_READER=torchvision` or `FORCE_QWENVL_VIDEO_READER=decord` if you prefer not to use the default one.
+
+| Backend     | HTTP | HTTPS |
+|-------------|------|-------|
+| torchvision >= 0.19.0 | ✅  | ✅   |
+| torchvision < 0.19.0  | ❌  | ❌   |
+| decord      | ✅  | ❌   |
+</details>
+
+<details>
+<summary>Batch inference</summary>
+
+```python
+# Sample messages for batch inference
+messages1 = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "file:///path/to/image1.jpg"},
+            {"type": "image", "image": "file:///path/to/image2.jpg"},
+            {"type": "text", "text": "What are the common elements in these pictures?"},
+        ],
+    }
+]
+messages2 = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Who are you?"},
+]
+# Combine messages for batch processing
+messages = [messages1, messages2]
+
+# Preparation for batch inference
+texts = [
+    processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
+    for msg in messages
+]
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=texts,
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
+
+# Batch Inference
+generated_ids = model.generate(**inputs, max_new_tokens=128)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_texts = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_texts)
+```
+</details>
+
+### 🤖 ModelScope
+We strongly advise users especially those in mainland China to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints.
+
+
+### More Usage Tips
+
+For input images, we support local files, base64, and URLs. For videos, we currently only support local files.
+
+```python
+# You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text.
+## Local file path
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "file:///path/to/your/image.jpg"},
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+## Image URL
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "http://path/to/your/image.jpg"},
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+## Base64 encoded image
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "data:image;base64,/9j/..."},
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+```
+#### Image Resolution for performance boost
+
+The model supports a wide range of resolution inputs. By default, it uses the native resolution for input, but higher resolutions can enhance performance at the cost of more computation. Users can set the minimum and maximum number of pixels to achieve an optimal configuration for their needs, such as a token count range of 256-1280, to balance speed and memory usage.
+
+```python
+min_pixels = 256 * 28 * 28
+max_pixels = 1280 * 28 * 28
+processor = AutoProcessor.from_pretrained(
+    "Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels
+)
+```
+
+Besides, We provide two methods for fine-grained control over the image size input to the model:
+
+1. Define min_pixels and max_pixels: Images will be resized to maintain their aspect ratio within the range of min_pixels and max_pixels.
+   
+2. Specify exact dimensions: Directly set `resized_height` and `resized_width`. These values will be rounded to the nearest multiple of 28.
+
+```python
+# min_pixels and max_pixels
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "file:///path/to/your/image.jpg",
+                "resized_height": 280,
+                "resized_width": 420,
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+# resized_height and resized_width
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "file:///path/to/your/image.jpg",
+                "min_pixels": 50176,
+                "max_pixels": 50176,
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
+```
+
+### Processing Long Texts
+
+The current `config.json` is set for context length up to 32,768 tokens.
+To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
+
+For supported frameworks, you could add the following to `config.json` to enable YaRN:
+
+{
+	...,
+    "type": "yarn",
+    "mrope_section": [
+        16,
+        24,
+        24
+    ],
+    "factor": 4,
+    "original_max_position_embeddings": 32768
+}
+
+However, it should be noted that this method has a significant impact on the performance of temporal and spatial localization tasks, and is therefore not recommended for use.
+
+At the same time, for long video inputs, since MRoPE itself is more economical with ids, the max_position_embeddings can be directly modified to a larger value, such as 64k.
+
+
+
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@misc{qwen2.5-VL,
+    title = {Qwen2.5-VL},
+    url = {https://qwenlm.github.io/blog/qwen2.5-vl/},
+    author = {Qwen Team},
+    month = {January},
+    year = {2025}
+}
+
+@article{Qwen2VL,
+  title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
+  author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
+  journal={arXiv preprint arXiv:2409.12191},
+  year={2024}
+}
+
+@article{Qwen-VL,
+  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
+  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
+  journal={arXiv preprint arXiv:2308.12966},
+  year={2023}
+}
+```

text_encoder/chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

text_encoder/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "intermediate_size": 3420,
+    "num_heads": 16,
+    "in_chans": 3,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "window_size": 112,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "tokens_per_second": 2,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 152064
+}

text_encoder/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.37.0"
+}

text_encoder/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97b877e47fde53a6c6e77aafb36e58e91ee9d95c4a3eeac6f1b5c0e6a1c986e
+size 3900233256

text_encoder/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a300a43b4724eee2abe7c18ceb26768d0ab011eb0cad19d9bfd2476a24d024
+size 3864726320

text_encoder/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111223d173e00bbee81cba1216fad28668df3476706b7fd26f4d5b50f8b3a507
+size 3864726424

text_encoder/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef47f634fa57d46ee134edcc09f34085a47da1e16c12a2abe0d67118be6d72ed
+size 3864733680

text_encoder/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c859795ad3a627a9b95bcb762e059d5b768a4a36fdd4affeff269d93fdecc67
+size 1089994880

text_encoder/model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00004-of-00005.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00005.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00005.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors"
+  }
+}

text_encoder_2/.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

text_encoder_2/README.md

@@ -0,0 +1,145 @@
+---
+tags:
+- vision
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
+  candidate_labels: playing music, playing sports
+  example_title: Cat & Dog
+---
+
+# Model Card: CLIP
+
+Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found [here](https://github.com/openai/CLIP/blob/main/model-card.md).
+
+## Model Details
+
+The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was also developed to test the ability of models to generalize to arbitrary image classification tasks in a zero-shot manner. It was not developed for general model deployment - to deploy models like CLIP, researchers will first need to carefully study their capabilities in relation to the specific context they’re being deployed within.
+
+### Model Date
+
+January 2021
+
+### Model Type
+
+The base model uses a ViT-L/14 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss.
+
+The original implementation had two variants: one using a ResNet image encoder and the other using a Vision Transformer. This repository has the variant with the Vision Transformer.
+
+
+### Documents
+
+- [Blog Post](https://openai.com/blog/clip/)
+- [CLIP Paper](https://arxiv.org/abs/2103.00020)
+
+
+### Use with Transformers
+
+```python
+from PIL import Image
+import requests
+
+from transformers import CLIPProcessor, CLIPModel
+
+model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)
+
+outputs = model(**inputs)
+logits_per_image = outputs.logits_per_image # this is the image-text similarity score
+probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
+```
+
+
+## Model Use
+
+### Intended Use
+
+The model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such models - the CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis.
+
+#### Primary intended uses
+
+The primary intended users of these models are AI researchers.
+
+We primarily imagine the model will be used by researchers to better understand robustness, generalization, and other capabilities, biases, and constraints of computer vision models.
+
+### Out-of-Scope Use Cases
+
+**Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. 
+
+Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
+
+Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
+
+
+
+## Data
+
+The model was trained on publicly available image-caption data. This was done through a combination of crawling a handful of websites and using commonly-used pre-existing image datasets such as [YFCC100M](http://projects.dfki.uni-kl.de/yfcc100m/). A large portion of the data comes from our crawling of the internet. This means that the data is more representative of people and societies most connected to the internet which tend to skew towards more developed nations, and younger, male users.
+
+### Data Mission Statement
+
+Our goal with building this dataset was to test out robustness and generalizability in computer vision tasks. As a result, the focus was on gathering large quantities of data from different publicly-available internet data sources. The data was gathered in a mostly non-interventionist manner. However, we only crawled websites that had policies against excessively violent and adult images and allowed us to filter out such content. We do not intend for this dataset to be used as the basis for any commercial or deployed model and will not be releasing the dataset.
+
+
+
+## Performance and Limitations
+
+### Performance
+
+We have evaluated the performance of CLIP on a wide range of benchmarks across a variety of computer vision datasets such as OCR to texture recognition to fine-grained classification. The paper describes model performance on the following datasets:
+
+- Food101
+- CIFAR10   
+- CIFAR100   
+- Birdsnap
+- SUN397
+- Stanford Cars
+- FGVC Aircraft
+- VOC2007
+- DTD
+- Oxford-IIIT Pet dataset
+- Caltech101
+- Flowers102
+- MNIST   
+- SVHN 
+- IIIT5K   
+- Hateful Memes   
+- SST-2
+- UCF101
+- Kinetics700
+- Country211
+- CLEVR Counting
+- KITTI Distance
+- STL-10
+- RareAct
+- Flickr30
+- MSCOCO
+- ImageNet
+- ImageNet-A
+- ImageNet-R
+- ImageNet Sketch
+- ObjectNet (ImageNet Overlap)
+- Youtube-BB
+- ImageNet-Vid
+
+## Limitations
+
+CLIP and our analysis of it have a number of limitations. CLIP currently struggles with respect to certain tasks such as fine grained classification and counting objects. CLIP also poses issues with regards to fairness and bias which we discuss in the paper and briefly in the next section. Additionally, our approach to testing CLIP also has an important limitation- in many cases we have used linear probes to evaluate the performance of CLIP and there is evidence suggesting that linear probes can underestimate model performance.
+
+### Bias and Fairness
+
+We find that the performance of CLIP - and the specific biases it exhibits - can depend significantly on class design and the choices one makes for categories to include and exclude. We tested the risk of certain kinds of denigration with CLIP by classifying images of people from [Fairface](https://arxiv.org/abs/1908.04913) into crime-related and non-human animal categories. We found significant disparities with respect to race and gender. Additionally, we found that these disparities could shift based on how the classes were constructed. (Details captured in the Broader Impacts Section in the paper).
+
+We also tested the performance of CLIP on gender, race and age classification using the Fairface dataset (We default to using race categories as they are constructed in the Fairface dataset.) in order to assess quality of performance across different demographics. We found accuracy >96% across all races for gender classification with ‘Middle Eastern’ having the highest accuracy (98.4%) and ‘White’ having the lowest (96.5%). Additionally, CLIP averaged ~93% for racial classification and ~63% for age classification. Our use of evaluations to test for gender, race and age classification as well as denigration harms is simply to evaluate performance of the model across people and surface potential risks and not to demonstrate an endorsement/enthusiasm for such tasks.
+
+
+
+## Feedback
+
+### Where to send questions or comments about the model
+
+Please use [this Google Form](https://forms.gle/Uv7afRH5dvY34ZEs9)

text_encoder_2/config.json

@@ -0,0 +1,171 @@
+{
+  "_name_or_path": "clip-vit-large-patch14/",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim" : 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.16.0.dev0",
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim" : 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.16.0.dev0",
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

text_encoder_2/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156f677ed4495acd1ec7197249c091b85c240267c82f2f7f2e4eae4177931fed
+size 1710486359

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bf730a0c7debf160f7a6b50b3aaf3703e7e88ac73de7a314903141db026dcb
+size 1710540580

text_encoder_2/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

text_encoder_2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a17cdbe0f36fec524f5cafb1c261ea3bbbc13e346e0f74fc9eb0460dedd0d3
+size 1710671599

text_encoder_2/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f154e925c18270d662d28f6261523c2ff6e80f1f05292cb034db41d5951c7a4
+size 1711114176

tokenizer/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "add_bos_token": false
+}

tokenizer_2/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+    "unk_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "bos_token": {
+        "content": "<|startoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": "<|endoftext|>",
+    "add_prefix_space": false,
+    "errors": "replace",
+    "do_lower_case": true,
+    "name_or_path": "openai/clip-vit-base-patch32",
+    "model_max_length": 77,
+    "special_tokens_map_file": "./special_tokens_map.json",
+    "tokenizer_class": "CLIPTokenizer"
+}