Instructions to use kaitchup/Llama-2-7b-gptq-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaitchup/Llama-2-7b-gptq-2bit with Transformers:

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

pipe = pipeline("text-generation", model="kaitchup/Llama-2-7b-gptq-2bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaitchup/Llama-2-7b-gptq-2bit")
model = AutoModelForCausalLM.from_pretrained("kaitchup/Llama-2-7b-gptq-2bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaitchup/Llama-2-7b-gptq-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaitchup/Llama-2-7b-gptq-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaitchup/Llama-2-7b-gptq-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kaitchup/Llama-2-7b-gptq-2bit

SGLang

How to use kaitchup/Llama-2-7b-gptq-2bit 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 "kaitchup/Llama-2-7b-gptq-2bit" \
    --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": "kaitchup/Llama-2-7b-gptq-2bit",
		"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 "kaitchup/Llama-2-7b-gptq-2bit" \
        --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": "kaitchup/Llama-2-7b-gptq-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kaitchup/Llama-2-7b-gptq-2bit with Docker Model Runner:
```
docker model run hf.co/kaitchup/Llama-2-7b-gptq-2bit
```

Model Card for Model ID

This is Meta's Llama 2 7B quantized in 2-bit using AutoGPTQ from Hugging Face Transformers.

Model Details

Model Description

Developed by: The Kaitchup
Model type: Causal (Llama 2)
Language(s) (NLP): English
License: Apache 2.0, Llama 2 license agreement

Model Sources

The method and code used to quantize the model are explained here: Quantize and Fine-tune LLMs with GPTQ Using Transformers and TRL

Uses

This model is pre-trained and not fine-tuned. You may fine-tune it with PEFT using adapters. Note that the 2-bit quantization significantly decreases the performance of Llama 2.

Other versions

Model Card Contact

The Kaitchup

Downloads last month: 22

Safetensors

Model size

7B params

Tensor type

I32

F16