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

Libraries

How to use ISTA-DASLab/gemma-2b-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/gemma-2b-AQLM-2Bit-1x16-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf")
model = AutoModelForMultimodalLM.from_pretrained("ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

docker model run hf.co/ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf

SGLang

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

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

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

Check out the documentation for more information.

Official AQLM quantization of google/gemma-2b.

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

Results (0-shot acc):

Model	Quantization	WinoGrande	PiQA	HellaSwag	ArcE	ArcC	Model size, Gb
gemma-2b	None	0.6472	0.7715	0.5279	0.7403	0.4053	5.0
	1x16	0.6275	0.7318	0.4582	0.6923	0.3259	1.7

To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the official GitHub repo.

Downloads last month: 302

Safetensors

Model size

0.8B params

Tensor type

F16

I16

Collection including ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf

AQLM

Collection

AQLM quantized LLMs • 21 items • Updated Feb 18 • 46

Paper for ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf

Extreme Compression of Large Language Models via Additive Quantization

Paper • 2401.06118 • Published Jan 11, 2024 • 14