Instructions to use eustlb/GLM-ASR-Nano-2512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eustlb/GLM-ASR-Nano-2512 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="eustlb/GLM-ASR-Nano-2512")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("eustlb/GLM-ASR-Nano-2512")
model = AutoModelForSeq2SeqLM.from_pretrained("eustlb/GLM-ASR-Nano-2512")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eustlb/GLM-ASR-Nano-2512 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eustlb/GLM-ASR-Nano-2512"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eustlb/GLM-ASR-Nano-2512",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eustlb/GLM-ASR-Nano-2512

SGLang

How to use eustlb/GLM-ASR-Nano-2512 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "eustlb/GLM-ASR-Nano-2512" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eustlb/GLM-ASR-Nano-2512",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "eustlb/GLM-ASR-Nano-2512" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eustlb/GLM-ASR-Nano-2512",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eustlb/GLM-ASR-Nano-2512 with Docker Model Runner:
```
docker model run hf.co/eustlb/GLM-ASR-Nano-2512
```

eustlb HF Staff commited on Dec 22, 2025

Commit

b08eccf

verified ·

1 Parent(s): 270644e

Upload processor

Browse files

Files changed (4) hide show

chat_template.jinja +37 -0
processor_config.json +20 -0
tokenizer.json +0 -0
tokenizer_config.json +32 -0

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,37 @@

+{%- macro to_text(content) -%}
+{%- if content is string -%}
+{{- content -}}
+{%- elif content is iterable and content is not mapping -%}
+{%- for item in content -%}
+{%- if item is mapping and item.type == 'text' and item.text is defined -%}
+{{- item.text -}}
+{%- elif item is mapping and (item.type == 'audio' or 'audio' in item) -%}
+<|begin_of_audio|><|pad|><|end_of_audio|><|user|>
+{% elif item is string -%}
+{{- item -}}
+{%- endif -%}
+{%- endfor -%}
+{%- else -%}
+{{- content -}}
+{%- endif -%}
+{%- endmacro -%}
+{%- for m in messages -%}
+{%- if m.role == 'system' -%}
+<|system|>
+{{ to_text(m.content) | trim }}
+{%- elif m.role == 'user' -%}
+<|user|>
+{{ to_text(m.content) | trim }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{{ to_text(m.content) | trim }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|assistant|>
+{% endif -%}

processor_config.json ADDED Viewed

	@@ -0,0 +1,20 @@

+{
+  "audio_bos_token": "<|begin_of_audio|>",
+  "audio_eos_token": "<|end_of_audio|>",
+  "audio_token": "<|pad|>",
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "feature_extractor_type": "WhisperFeatureExtractor",
+    "feature_size": 128,
+    "hop_length": 160,
+    "n_fft": 400,
+    "n_samples": 480000,
+    "nb_max_frames": 3000,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": false,
+    "sampling_rate": 16000
+  },
+  "processor_class": "GlmasrProcessor"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>"
+  ],
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 65536,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "GlmasrProcessor",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}