Instructions to use kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ")
model = AutoModelForCausalLM.from_pretrained("kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ"
# 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-3-8B-4bit-AutoRound-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ

SGLang

How to use kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ 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-3-8B-4bit-AutoRound-GPTQ" \
    --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-3-8B-4bit-AutoRound-GPTQ",
		"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-3-8B-4bit-AutoRound-GPTQ" \
        --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-3-8B-4bit-AutoRound-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ with Docker Model Runner:
```
docker model run hf.co/kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This model is exclusively available to paid subscribers of The Kaitchup. To gain access, subscribe to The Kaitchup for either a monthly or yearly paid plan. Once subscribed, you will receive an access token by email and will have access to all the models listed on this page.

Model Details

This is meta-llama/Meta-Llama-3-8B quantized with AutoRound and serialized with the GPTQ format in 4-bit. The model has been created, tested, and evaluated by The Kaitchup.

Details on the AutoRound quantization process and how to use the model here: Intel AutoRound: Accurate Low-bit Quantization for LLMs

Developed by: The Kaitchup
Language(s) (NLP): English
License: cc-by-4.0

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F16

I32

Collection including kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ

[Basics] AutoRound: Llama 3

Collection

2 items • Updated Jun 28, 2024