Instructions to use princeton-nlp/Sheared-LLaMA-2.7B-Pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use princeton-nlp/Sheared-LLaMA-2.7B-Pruned with Transformers:

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

pipe = pipeline("text-generation", model="princeton-nlp/Sheared-LLaMA-2.7B-Pruned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/Sheared-LLaMA-2.7B-Pruned")
model = AutoModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-2.7B-Pruned")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use princeton-nlp/Sheared-LLaMA-2.7B-Pruned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "princeton-nlp/Sheared-LLaMA-2.7B-Pruned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "princeton-nlp/Sheared-LLaMA-2.7B-Pruned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/princeton-nlp/Sheared-LLaMA-2.7B-Pruned

SGLang

How to use princeton-nlp/Sheared-LLaMA-2.7B-Pruned 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 "princeton-nlp/Sheared-LLaMA-2.7B-Pruned" \
    --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": "princeton-nlp/Sheared-LLaMA-2.7B-Pruned",
		"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 "princeton-nlp/Sheared-LLaMA-2.7B-Pruned" \
        --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": "princeton-nlp/Sheared-LLaMA-2.7B-Pruned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use princeton-nlp/Sheared-LLaMA-2.7B-Pruned with Docker Model Runner:
```
docker model run hf.co/princeton-nlp/Sheared-LLaMA-2.7B-Pruned
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

license: llama2

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
Pruned Models without Continued Pre-training: Sheared-LLaMA-1.3B-Pruned, Sheared-LLaMA-2.7B-Pruned Instruction-tuned Models: Sheared-LLaMA-1.3B-ShareGPT, Sheared-LLaMA-2.7B-ShareGPT

License: Must comply with license of Llama2 since it's a model derived from Llama2.

Sheared-LLaMA-2.7B-Pruned is the model pruned from meta-llama/Llama-2-7b-hf without continued pre-training. We used roughly 0.4B tokens to perform the pruning experiment. This model could be a good use to study

effective data mixtures for continued pre-training
comparisons to other pruning techniques
extensive evaluations to understand how pruning affects knowledge and reasoning capabilities of LLMs

Downloads last month: 4

Model tree for princeton-nlp/Sheared-LLaMA-2.7B-Pruned

Quantizations

2 models

Collection including princeton-nlp/Sheared-LLaMA-2.7B-Pruned

Sheared Llama

Collection

7 items • Updated Mar 8, 2025 • 2

Paper for princeton-nlp/Sheared-LLaMA-2.7B-Pruned

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

Paper • 2310.06694 • Published Oct 10, 2023 • 3