README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - Mistral
  - instruct
  - finetune
  - chatml
  - DPO
  - RLHF
  - gpt4
  - synthetic data
  - distillation
  - function calling
  - json mode
  - mlx
base_model: NousResearch/Hermes-2-Pro-Mistral-7B
datasets:
  - teknium/OpenHermes-2.5
widget:
  - example_title: Hermes 2 Pro
    messages:
      - role: system
        content: >-
          You are a sentient, superintelligent artificial general intelligence,
          here to teach and assist me.
      - role: user
        content: >-
          Write a short story about Goku discovering kirby has teamed up with
          Majin Buu to destroy the world.
model-index:
  - name: Hermes-2-Pro-Mistral-7B
    results: []

mlx-community/Hermes-2-Pro-Mistral-7B-3bit

The Model mlx-community/Hermes-2-Pro-Mistral-7B-3bit was converted to MLX format from NousResearch/Hermes-2-Pro-Mistral-7B using mlx-lm version 0.20.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Hermes-2-Pro-Mistral-7B-3bit")

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)