MLX
mistral
Merge
mergekit
lazymergekit
fblgit/UNA-TheBeagle-7b-v1
argilla/distilabeled-Marcoro14-7B-slerp
dpo
rlhf
Instructions to use mlx-community/NeuralBeagle14-7B-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/NeuralBeagle14-7B-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir NeuralBeagle14-7B-4bit-mlx mlx-community/NeuralBeagle14-7B-4bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
NeuralBeagle14-7B-4bit-MLX to perform MLX - RAG
#1
by discovertheunknown - opened
Create a vector database from any of your pdf(s) and "RAG it" on MLX with (for example) this NeuralBeagle14-7B-4bit-MLX LLM.
Complete code: https://github.com/vegaluisjose/mlx-rag
Take any pdf, create a vector db, "RAG it"!
mc0ps changed discussion status to closed