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

Libraries

How to use BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch")
model = AutoModelForCausalLM.from_pretrained("BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch

SGLang

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

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

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

Check out the documentation for more information.

WARNING: this checkpoint might be obsolete. Please use the updated Mixtral checkpoint.

Official AQLM quantization of mistralai/Mixtral-8x7B-v0.1.

Downloads last month: 29

Safetensors

Model size

7B params

Tensor type

F16

I16

Paper for BlackSamorez/Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch

Extreme Compression of Large Language Models via Additive Quantization

Paper • 2401.06118 • Published Jan 11, 2024 • 15