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")

Notebooks
Google Colab
Kaggle
Local Apps

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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Update 12/27/2023: We have released an updated version of this model with similar performance and a more permissive license at https://huggingface.co/OpenPipe/mistral-ft-optimized-1227. We recommend that model over this one for most users.

This model is intended to be a strong base suitable for downstream fine-tuning on a variety of tasks. Based on our internal evaluations, we believe it's one of the strongest models for most down-stream tasks. You can read more about our development and evaluation process here.

Mergekit config used to create this model:

slices:
  - sources:
      - model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
        layer_range: [0, 32]
      - model: Q-bert/MetaMath-Cybertron-Starling
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

Note: It appears that https://huggingface.co/Weyaxi/Seraph-7B was merged from the same base models using the same mergekit defaults as this model. So major credit goes to @Weyaxi both for creating one of the base merges this model was merged from, as well as being the first one to perform this exact merge as well!

Downloads last month: 278

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for OpenPipe/mistral-ft-optimized-1218

Adapters

1 model

Finetunes

1 model

Merges

162 models

Quantizations

6 models

OpenPipe
/

mistral-ft-optimized-1218

Model tree for OpenPipe/mistral-ft-optimized-1218

Spaces using OpenPipe/mistral-ft-optimized-1218 3