Instructions to use ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-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/Llama-2-13b-AQLM-2Bit-2x8-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf

SGLang

How to use ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-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/Llama-2-13b-AQLM-2Bit-2x8-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/Llama-2-13b-AQLM-2Bit-2x8-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/Llama-2-13b-AQLM-2Bit-2x8-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/Llama-2-13b-AQLM-2Bit-2x8-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf
```

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

Check out the documentation for more information.

Official AQLM quantization of meta-llama/Llama-2-13b-hf.

For this quantization, we used 2 codebook of 8 bits.

Selected evaluation results for this and other models:

Model	Quantization	WikiText 2 PPL	Model size, Gb
Llama-2-13b	-	4.57	26.0
	2x8	5.63	3.8

Downloads last month: 22

Safetensors

Model size

4B params

Tensor type

F16

Paper for ISTA-DASLab/Llama-2-13b-AQLM-2Bit-2x8-hf

Extreme Compression of Large Language Models via Additive Quantization

Paper • 2401.06118 • Published Jan 11, 2024 • 14