Instructions to use tencent/Hunyuan-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hunyuan-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hunyuan-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tencent/Hunyuan-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("tencent/Hunyuan-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tencent/Hunyuan-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hunyuan-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Hunyuan-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hunyuan-7B-Instruct

SGLang

How to use tencent/Hunyuan-7B-Instruct 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 "tencent/Hunyuan-7B-Instruct" \
    --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": "tencent/Hunyuan-7B-Instruct",
		"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 "tencent/Hunyuan-7B-Instruct" \
        --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": "tencent/Hunyuan-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hunyuan-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/tencent/Hunyuan-7B-Instruct
```

fix chat template

#10

by kallewooof - opened Nov 5, 2025

base: refs/heads/main

←

from: refs/pr/10

Discussion Files changed

+27

-3

Files changed (2) hide show

chat_template.jinja +25 -0
tokenizer_config.json +2 -3

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,25 @@

+{%- set ns = namespace(has_head=true) -%}
+{%- set loop_messages = messages -%}
+{%- for message in loop_messages -%}
+    {%- set content = message['content'] -%}
+    {%- if loop.index0 == 0 -%}
+        {%- if content == '' -%}
+            {%- set ns.has_head = false -%}
+        {%- elif message['role'] == 'system' -%}
+            {%- set content = '<|startoftext|>' + content + '<|extra_4|>' -%}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if message['role'] == 'user' -%}
+        {%- if loop.index0 == 1 and not ns.has_head -%}
+            {%- set content = '<|startoftext|>' + content -%}
+        {%- endif -%}
+        {%- if loop.index0 == 1 and ns.has_head -%}
+            {%- set content = content + '<|extra_0|>' -%}
+        {%- else -%}
+            {%- set content = '<|startoftext|>' + content + '<|extra_0|>' -%}
+        {%- endif -%}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- set content = content + '<|eos|>' -%}
+    {%- endif -%}
+    {{- content -}}
+{%- endfor -%}

tokenizer_config.json CHANGED Viewed

@@ -4,6 +4,5 @@
   "eos_token": "<|eos|>",
   "model_max_length": 262144,
   "pad_token": "<|pad|>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "chat_template": "{% set context = {'has_head': true} %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 %}{% if content == '' %}{% set _ = context.update({'has_head': false}) %}{% elif message['role'] == 'system' %}{% set content = '<|startoftext|>' + content + '<|extra_4|>' %}{% endif %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 1 and not context.has_head %}{% set content = '<|startoftext|>' + content %}{% endif %}{% if loop.index0 == 1 and context.has_head %}{% set content = content + '<|extra_0|>' %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_0|>' %}{% endif %}{% elif message['role'] == 'assistant' %}{% set content = content + '<|eos|>' %}{% endif %}{{ content }}{% endfor %}"
-}

   "eos_token": "<|eos|>",
   "model_max_length": 262144,
   "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}