Instructions to use Gustrd/open-llama-13b-4bit-128g-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gustrd/open-llama-13b-4bit-128g-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="Gustrd/open-llama-13b-4bit-128g-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gustrd/open-llama-13b-4bit-128g-GPTQ")
model = AutoModelForCausalLM.from_pretrained("Gustrd/open-llama-13b-4bit-128g-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Gustrd/open-llama-13b-4bit-128g-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gustrd/open-llama-13b-4bit-128g-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gustrd/open-llama-13b-4bit-128g-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Gustrd/open-llama-13b-4bit-128g-GPTQ

SGLang

How to use Gustrd/open-llama-13b-4bit-128g-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 "Gustrd/open-llama-13b-4bit-128g-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": "Gustrd/open-llama-13b-4bit-128g-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 "Gustrd/open-llama-13b-4bit-128g-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": "Gustrd/open-llama-13b-4bit-128g-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Gustrd/open-llama-13b-4bit-128g-GPTQ with Docker Model Runner:
```
docker model run hf.co/Gustrd/open-llama-13b-4bit-128g-GPTQ
```

Summary

This is a 4bit quantised openlm-research/open_llama_13b using GPTQ-for-LLaMa.

The quantization command was: python ./GPTQ-for-LLaMa/llama.py ./open_llama_13b c4 --wbits 4 --true-sequential --groupsize 128 --save open-llama-13b-4bit-128g.pt

Original model readme is below.

OpenLLaMA: An Open Reproduction of LLaMA

In this repo, we present a permissively licensed open source reproduction of Meta AI's LLaMA large language model. We are releasing 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA models, as well as evaluation results and comparison against the original LLaMA models. Please see the project homepage of OpenLLaMA for more details. (continue at https://huggingface.co/openlm-research/open_llama_13b)

Downloads last month: 19

Model tree for Gustrd/open-llama-13b-4bit-128g-GPTQ

Adapters

1 model