Instructions to use ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf

SGLang

How to use ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 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 "ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf" \
    --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": "ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf",
		"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 "ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf" \
        --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": "ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf
```

Loading Model on AWS G5.4xlarge Instance Results in 'killed' Message

by Tejasram - opened Feb 10, 2024

Discussion

Tejasram

Feb 10, 2024

I'm trying to implement a RAG system using this model on an aws g5.4xlarge instance with the following configurations:
vcpus: 16
gpu: NVidia A10g 24GB

This is the code im using:
model_path = "BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf" tokenizer_path = "mistralai/Mixtral-8x7B-v0.1"


tokenizer = AutoTokenizer.from_pretrained(model_path)
pipe = pipeline("text2text-generation",model=model_path,tokenizer=tokenizer,trust_remote_code=True,max_new_tokens=1000)

However when i run this, the process gets killed.

BlackSamorez

IST Austria Distributed Algorithms and Systems Lab org Feb 10, 2024

I haven't worked with AWS so I'm not sure what killed might mean, but it's likely that you don't have enough RAM to load the model.
One thing you could do is install the latest accelerate in your environment

pip install git+https://github.com/huggingface/accelerate.git@main

and then load the model with extra kwarg device_map="cuda". That would cut RAM requirements significantly.

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