Instructions to use Qwen/Qwen2-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-7B-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Qwen/Qwen2-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2-7B-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": "Qwen/Qwen2-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2-7B-Instruct

SGLang

How to use Qwen/Qwen2-7B-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 "Qwen/Qwen2-7B-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": "Qwen/Qwen2-7B-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 "Qwen/Qwen2-7B-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": "Qwen/Qwen2-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2-7B-Instruct
```

Unable to run the model properly

by zaz423129 - opened Jun 13, 2024

Discussion

zaz423129

Jun 13, 2024

code:
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
"/home/llmuser/LLM_Z/my_projects/Qwen2-7B-Instruct",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("/home/llmuser/LLM_Z/my_projects/Qwen2-7B-Instruct")

prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

The error is as follows
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
File "/home/llmuser/LLaMA-Factory/Qwen-7B.py", line 23, in
generated_ids = model.generate(
File "/home/llmuser/anaconda3/envs/fine-tuning/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/llmuser/anaconda3/envs/fine-tuning/lib/python3.10/site-packages/transformers/generation/utils.py", line 1758, in generate
result = self._sample(
File "/home/llmuser/anaconda3/envs/fine-tuning/lib/python3.10/site-packages/transformers/generation/utils.py", line 2410, in _sample
next_token_scores = logits_processor(input_ids, next_token_logits)
File "/home/llmuser/anaconda3/envs/fine-tuning/lib/python3.10/site-packages/transformers/generation/logits_process.py", line 98, in call
scores = processor(input_ids, scores)
File "/home/llmuser/anaconda3/envs/fine-tuning/lib/python3.10/site-packages/transformers/generation/logits_process.py", line 341, in call
score = torch.gather(scores, 1, input_ids)
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

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