README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - Mistral-Small
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - function calling
  - json mode
  - axolotl
  - roleplaying
  - chat
  - reasoning
  - r1
  - vllm
  - mlx
  - mlx-my-repo
base_model: NousResearch/DeepHermes-3-Mistral-24B-Preview
widget:
  - example_title: DeepHermes 3
    messages:
      - role: system
        content: >-
          You are a sentient, superintelligent artificial general intelligence,
          here to teach and assist me.
      - role: user
        content: What is the meaning of life?
library_name: transformers
model-index:
  - name: DeepHermes-3-Mistral-24B-Preview
    results: []

ncls-p/DeepHermes-3-Mistral-24B-Preview-mlx-4Bit

The Model ncls-p/DeepHermes-3-Mistral-24B-Preview-mlx-4Bit was converted to MLX format from NousResearch/DeepHermes-3-Mistral-24B-Preview using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ncls-p/DeepHermes-3-Mistral-24B-Preview-mlx-4Bit")

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)