Instructions to use Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8")
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 Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8

SGLang

How to use Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 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 "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8" \
    --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": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8",
		"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 "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8" \
        --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": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8
```

Weird repetition issue

by AlioLeuchtmann - opened Jan 29, 2025

Discussion

AlioLeuchtmann

Jan 29, 2025

•

edited Jan 29, 2025

running with vllm
--model Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8
--trust-remote-code
--host 0.0.0.0
--port 8001
--max-model-len 10000
--tensor-parallel-size 4
--gpu_memory_utilization 0.8

When prompted with: "3+3"

it does repeat 3+3 until max sequence length

Received request cmpl-86e5261a2d4247719d83a2e7fb08d88d-13: prompt: '3+3', params: SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.0, top_p=1.0, top_k=-1, min_p=0.0, seed=None, stop=[], stop_token_ids=[
], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=3000, min_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None), prompt_token_ids: [3838, 374, 220, 18, 10, 18], lora_request: None, prompt_adapter_request: None.

Any Ideas ?

Edit: Hmm Same happens on unquant Version, maybe missing system template ?
Edit2: temp=0.7 fixes this behaviour for the tested prompts.
Previously tested with fireworksai temp 0.0 -> they might dont even apply the sampling params who knows.
Edit3: Does only fix for batch size of 1
Might be related to vllm
https://github.com/vllm-project/vllm/issues/5898

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment