Instructions to use mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ with Transformers:

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

pipe = pipeline("text-generation", model="mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ")
model = AutoModelForCausalLM.from_pretrained("mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ

SGLang

How to use mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ 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 "mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ" \
    --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": "mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ",
		"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 "mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ" \
        --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": "mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ with Docker Model Runner:
```
docker model run hf.co/mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ
```

Llama-2-70b-hf-2bit_g16_s128-HQQ {Deprecated}

This is a version of the LLama-2-70B-hf model quantized to 2-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/

This model outperforms an fp16 LLama-2-13B (perplexity 4.13 vs. 4.63) for a comparable ~26GB size.

Warning: this model is deprecated, it requires an older version of hqq.

To run the model, install the HQQ library:

#This model is deprecated and requires older versions
pip install hqq==0.1.8
pip install transformers==4.46.0

and use it as follows:

model_id = 'mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ'

from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)
model     = HQQModelForCausalLM.from_quantized(model_id)

Limitations:
-Only supports single GPU runtime.
-Not compatible with HuggingFace's PEFT.

Downloads last month: 19

Collection including mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ

Llama2 HQQ Quantized Models

Collection

LLama2 models quantized using https://github.com/mobiusml/hqq • 6 items • Updated Mar 29, 2024 • 6