Instructions to use ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf")
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-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/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf

SGLang

How to use ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-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/Meta-Llama-3.1-8B-AQLM-PV-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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf",
		"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 "ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf
```

Official AQLM quantization of meta-llama/Meta-Llama-3.1-8B finetuned with PV-Tuning.

For this quantization, we used 1 codebook of 16 bits and groupsize of 8.

Results:

Model	Quantization	MMLU (5-shot)	ArcC	ArcE	Hellaswag	PiQA	Winogrande	Model size, Gb
meta-llama/Meta-Llama-3.1-8B	None	0.6521	0.5145	0.8144	0.5998	0.8014	0.7356	16.1
	1x16g8	0.5746	0.4454	0.7744	0.5629	0.7954	0.7024	4.1

Note

We used lm-eval=0.4.0 for evaluation.

UPD (09.08.2024)

Uploaded new version finetuned on more data for longer with better quality.

Downloads last month: 99

Safetensors

Model size

2B params

Tensor type

F16

I16

Collection including ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf

AQLM+PV

Collection

Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852 • 26 items • Updated Feb 18 • 22

Papers for ISTA-DASLab/Meta-Llama-3.1-8B-AQLM-PV-2Bit-1x16-hf

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

Paper • 2405.14852 • Published May 23, 2024 • 2

Extreme Compression of Large Language Models via Additive Quantization

Paper • 2401.06118 • Published Jan 11, 2024 • 14