Instructions to use openlm-research/open_llama_7b_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlm-research/open_llama_7b_v2 with Transformers:

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

pipe = pipeline("text-generation", model="openlm-research/open_llama_7b_v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlm-research/open_llama_7b_v2")
model = AutoModelForCausalLM.from_pretrained("openlm-research/open_llama_7b_v2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openlm-research/open_llama_7b_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openlm-research/open_llama_7b_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openlm-research/open_llama_7b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlm-research/open_llama_7b_v2

SGLang

How to use openlm-research/open_llama_7b_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 "openlm-research/open_llama_7b_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": "openlm-research/open_llama_7b_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 "openlm-research/open_llama_7b_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": "openlm-research/open_llama_7b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlm-research/open_llama_7b_v2 with Docker Model Runner:
```
docker model run hf.co/openlm-research/open_llama_7b_v2
```

Apache 2.0 License

by ai-agi - opened Oct 29, 2023

Discussion

ai-agi

Oct 29, 2023

Dear authors,

Being Open Llama derived from original Llama directly or indirectly, has Meta given explicit permission to your group to license Open Llama under Apache 2.0 License?
Thank you.
Best,
Marc

JLouisBiz

Dec 26, 2024

Question wasn't answered, and now is Thursday 26 December 2024

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