README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - mistral
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - dpo
  - rlhf
  - mlx
datasets:
  - mlabonne/chatml_dpo_pairs
base_model: teknium/OpenHermes-2.5-Mistral-7B

sugatoray/mlx-neuralhermes-2.5-mistral-7b-q4bits

This model was converted to MLX format from mlabonne/NeuralHermes-2.5-Mistral-7B. 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("sugatoray/mlx-neuralhermes-2.5-mistral-7b-q4bits")
response = generate(model, tokenizer, prompt="hello", verbose=True)