Instructions to use OpenPipe/mistral-ft-optimized-1218 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenPipe/mistral-ft-optimized-1218 with Transformers:

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

pipe = pipeline("text-generation", model="OpenPipe/mistral-ft-optimized-1218")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenPipe/mistral-ft-optimized-1218")
model = AutoModelForCausalLM.from_pretrained("OpenPipe/mistral-ft-optimized-1218", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenPipe/mistral-ft-optimized-1218 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenPipe/mistral-ft-optimized-1218"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenPipe/mistral-ft-optimized-1218",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenPipe/mistral-ft-optimized-1218

SGLang

How to use OpenPipe/mistral-ft-optimized-1218 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 "OpenPipe/mistral-ft-optimized-1218" \
    --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": "OpenPipe/mistral-ft-optimized-1218",
		"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 "OpenPipe/mistral-ft-optimized-1218" \
        --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": "OpenPipe/mistral-ft-optimized-1218",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenPipe/mistral-ft-optimized-1218 with Docker Model Runner:
```
docker model run hf.co/OpenPipe/mistral-ft-optimized-1218
```

🚩 Report: Legal issue(s)

by Vesu - opened Dec 27, 2023

Discussion

Vesu

Dec 27, 2023

The model claims to be Apache licensed, but is a merge of a model that is CC-BY-NC

corbt

OpenPipe org Dec 27, 2023

•

edited Dec 27, 2023

Thanks for bringing this to our attention. We'll investigate the licensing issue and update the license here if necessary.

UPDATE: yes, it appears that of the 5 base models included in this merge, one of them (Starling) has a cc-by-nc license, which means this model should have a cc-by-nc license as well. I'll update the license now and work on identifying a new set of base models that give similar performance without the nc restrictions.

Vesu changed discussion status to closed Dec 30, 2023

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