Instructions to use gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax with Transformers:

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

pipe = pipeline("text-generation", model="gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax")
model = AutoModelForCausalLM.from_pretrained("gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax

SGLang

How to use gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax 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 "gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax" \
    --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": "gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax",
		"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 "gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax" \
        --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": "gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax with Docker Model Runner:
```
docker model run hf.co/gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax
```

Paper: https://arxiv.org/pdf/2310.06694.pdf
Code: https://github.com/princeton-nlp/LLM-Shearing
Models: Sheared-LLaMA-1.3B, Sheared-LLaMA-2.7B

Training information

This is the instruction tuned version of princeton-nlp/Sheared-LLaMA-1.3B. We trained the base model on 10,000 instruction-response pairs sampled from the ShareGPT dataset (first-turns only). We use the following prompt to perform instruction tuning.

You are a helpful assistant. Write a response that appropriately completes the request.\n\n### Input:\n{input}\n\n### Response:

This model can be loaded through transformers.LlamaModelForCausalLM as follows:

from transformers import LlamaModelForCausalLM
model = LlamaModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-1.3B-ShareGPT")

Bibtex

If you find our model useful, consider citing us with:

@article{xia2023sheared,
  title={Sheared llama: Accelerating language model pre-training via structured pruning},
  author={Xia, Mengzhou and Gao, Tianyu and Zeng, Zhiyuan and Chen, Danqi},
  journal={arXiv preprint arXiv:2310.06694},
  year={2023}
}

Downloads last month: 2

Paper for gradientai/Sheared-LLaMA-1.3B-ShareGPT-jax

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Paper • 2310.06694 • Published Oct 10, 2023 • 3