README.md

metadata

base_model: teknium/OpenHermes-2.5-Mistral-7B
datasets:
  - teknium/OpenHermes-2.5
language:
  - en
license: apache-2.0
tags:
  - mistral
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - mlx
model-index:
  - name: OpenHermes-2-Mistral-7B
    results: []

TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-104ce

The Model TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-104ce was converted to MLX format from teknium/OpenHermes-2.5-Mistral-7B using mlx-lm version 0.20.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-104ce")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)