Instructions to use Qwen/Qwen1.5-MoE-A2.7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen1.5-MoE-A2.7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen1.5-MoE-A2.7B-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-MoE-A2.7B-Chat")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-MoE-A2.7B-Chat", device_map="auto")
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 Settings

vLLM

How to use Qwen/Qwen1.5-MoE-A2.7B-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen1.5-MoE-A2.7B-Chat"
# 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/Qwen1.5-MoE-A2.7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen1.5-MoE-A2.7B-Chat

SGLang

How to use Qwen/Qwen1.5-MoE-A2.7B-Chat 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/Qwen1.5-MoE-A2.7B-Chat" \
    --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/Qwen1.5-MoE-A2.7B-Chat",
		"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/Qwen1.5-MoE-A2.7B-Chat" \
        --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/Qwen1.5-MoE-A2.7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen1.5-MoE-A2.7B-Chat with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen1.5-MoE-A2.7B-Chat
```

请问这个版本GPU内存消耗28G与14B对比如何?

by william0014 - opened Apr 6, 2024

Discussion

william0014

Apr 6, 2024

这个MoE版本, GPU显存消耗与14B一样, 但是却只有7B的能力, MoE这个作用是什么呢?

shing3232

Apr 6, 2024

因为他int4 moe 只有4G

bzheng

Qwen org Apr 7, 2024

•

edited Apr 7, 2024

推理速度是 7B 的 1.74 倍

william0014

Apr 7, 2024

推理速度是 7B 的 1.74 倍

但是效果只有7B, 和14B有一定差距, 它的显存消耗和14B一样, 显存占用和14B的接近,但是推理效果比14B差一点, 所以我比较疑惑这个版本主要使用场景是什么?

shing3232

Apr 9, 2024

推理速度是 7B 的 1.74 倍

但是效果只有7B, 和14B有一定差距, 它的显存消耗和14B一样, 显存占用和14B的接近,但是推理效果比14B差一点, 所以我比较疑惑这个版本主要使用场景是什么?

量化后的显存使用应该是 7B的感觉

everythingRequireConfirm

Apr 18, 2024

This comment has been hidden

JustinLin610

Apr 24, 2024

This is about why we need MoE models. The model is large, but for each forward pass, the number of activated parameters is only 2.7B. This means that for the deployment, you can increase the throughput and and you can enjoy the benefits of acceleration.

jony4

May 13, 2024

https://qwenlm.github.io/zh/blog/qwen-moe/ 官方博文有解释

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