Instructions to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Mistral-7B-Instruct-v0.1-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Mistral-7B-Instruct-v0.1-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ

SGLang

How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ 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 "TheBloke/Mistral-7B-Instruct-v0.1-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TheBloke/Mistral-7B-Instruct-v0.1-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Mistral-7B-Instruct-v0.1-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Mistral-7B-Instruct-v0.1-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ
```

AWQ models with transformer pipeline

by RaviNaik - opened Oct 18, 2023

Discussion

RaviNaik

Oct 18, 2023

Hi, is there any way to use AWQ quantized models with transformers pipeline? Getting this error when tried to use the AWQ model with pipeline.
AttributeError: 'MistralAWQForCausalLM' object has no attribute 'config'

Thanks

Lord-Goku

Oct 21, 2023

I am having the same problem

RaviNaik

Oct 28, 2023

@Lord-Goku Please use model.model instead of just model for model argument of the pipeline method.
Ex:

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model=model.model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1,
)

print(pipe(prompt)[0]["generated_text"])

TheBloke

Owner Oct 28, 2023

That works? Nice, thanks @RaviNaik !

Note that very soon there will be native support for AWQ in Transformers, and then pipeline should work as normal without special steps needed.

RaviNaik

Oct 28, 2023

Yeah it works @TheBloke , tested it out with TheBloke/Mistral-7B-Instruct-v0.1-AWQ.
One more issue I noticed is that AutoAWQForCausalLM.from_quantized by default loads the model into cuda:0 or device0 and it looks like there is no device_map kind of argument we can pass to specify the device index. Hope these issues will be solved once AWQ is natively supported in Transformers.

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