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

Libraries

How to use princeton-nlp/Sheared-LLaMA-2.7B 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")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

Docker Model Runner
How to use princeton-nlp/Sheared-LLaMA-2.7B with Docker Model Runner:
```
docker model run hf.co/princeton-nlp/Sheared-LLaMA-2.7B
```

mistral

by Aryanne - opened Oct 12, 2023

Discussion

Aryanne

Oct 12, 2023

can you do the same with mistral?

princeton-nlp

Owner Oct 12, 2023

Yes, I think the idea applies to mistral.

appvoid

Oct 13, 2023

I'm really excited to see where this goes!

vasilee

Oct 13, 2023

Yes, I think the idea applies to mistral.

this model looks extremely good for a base model, I would like to see a fine-tuned version (e.g. OpenOrca),
for tasks like answering from the context (RAG), we don't need big models,
so I would say a Mistral little brother with the same big context (32K) and architecture (Grouped-query attention and Sliding Window Attention) and fine-tuned to follow instructions (e.g. Mistral-7B-OpenOrca) is more than enough

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment