Instructions to use sardukar/llama13b-4bit-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sardukar/llama13b-4bit-v2 with Transformers:

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

pipe = pipeline("text-generation", model="sardukar/llama13b-4bit-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sardukar/llama13b-4bit-v2")
model = AutoModelForCausalLM.from_pretrained("sardukar/llama13b-4bit-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sardukar/llama13b-4bit-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sardukar/llama13b-4bit-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sardukar/llama13b-4bit-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sardukar/llama13b-4bit-v2

SGLang

How to use sardukar/llama13b-4bit-v2 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 "sardukar/llama13b-4bit-v2" \
    --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": "sardukar/llama13b-4bit-v2",
		"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 "sardukar/llama13b-4bit-v2" \
        --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": "sardukar/llama13b-4bit-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sardukar/llama13b-4bit-v2 with Docker Model Runner:
```
docker model run hf.co/sardukar/llama13b-4bit-v2
```

Quantized Meta AI's LLaMA in 4bit with the help of GPTQ algorithm v2.

llama13b-4bit-ts-ao-g128-v2.safetensors GPTQ implementation - https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/49efe0b67db4b40eac2ae963819ebc055da64074

Conversion process:

CUDA_VISIBLE_DEVICES=0 python llama.py ./llama-13b c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors ./q4/llama13b-4bit-ts-ao-g128-v2.safetensors

llama13b-4bit-v2.safetensors GPTQ implementation - https://github.com/qwopqwop200/GPTQ-for-LLaMa/tree/841feedde876785bc8022ca48fd9c3ff626587e2

Note: This model will fail to load with current GPTQ-for-LLaMa implementation

Conversion process

CUDA_VISIBLE_DEVICES=0 python llama.py ./llama-13b c4 --wbits 4 --true-sequential --act-order  --save_safetensors ./q4/llama13b-4bit-v2.safetensors

Downloads last month: 12

Papers for sardukar/llama13b-4bit-v2

LLaMA: Open and Efficient Foundation Language Models

Paper • 2302.13971 • Published Feb 27, 2023 • 25

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Paper • 2210.17323 • Published Oct 31, 2022 • 12