Instructions to use RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits", 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 RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits

SGLang

How to use RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits 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 "RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits" \
    --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": "RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits",
		"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 "RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits" \
        --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": "RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/Qwen_-_Qwen1.5-MoE-A2.7B-4bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen1.5-MoE-A2.7B - bnb 4bits

Model creator: https://huggingface.co/Qwen/
Original model: https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B/

Original model description:

license: other license_name: tongyi-qianwen license_link: >- https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B/blob/main/LICENSE language: - en pipeline_tag: text-generation tags: - pretrained - moe

Qwen1.5-MoE-A2.7B

Introduction

Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data.

For more details, please refer to our blog post and GitHub repo.

Model Details

Qwen1.5-MoE employs Mixture of Experts (MoE) architecture, where the models are upcycled from dense language models. For instance, Qwen1.5-MoE-A2.7B is upcycled from Qwen-1.8B. It has 14.3B parameters in total and 2.7B activated parameters during runtime, while achieving comparable performance to Qwen1.5-7B, it only requires 25% of the training resources. We also observed that the inference speed is 1.74 times that of Qwen1.5-7B.

Requirements

The code of Qwen1.5-MoE has been in the latest Hugging face transformers and we advise you to build from source with command pip install git+https://github.com/huggingface/transformers, or you might encounter the following error:

KeyError: 'qwen2_moe'.

Usage

We do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.

Downloads last month: 6

Safetensors

Model size

15B params

Tensor type

F32

F16