README.md

metadata

tags:
  - alignment-handbook
  - generated_from_trainer
  - mlx
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
  - HuggingFaceH4/orca_dpo_pairs
base_model: HuggingFaceH4/starchat2-15b-sft-v0.1
model-index:
  - name: starchat2-15b-v0.1
    results: []

mlx-community/starchat2-15b-v0.1-4bit

This model was converted to MLX format from HuggingFaceH4/starchat2-15b-v0.1. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/starchat2-15b-v0.1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)