README.md

metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
tags:
  - openhermes
  - mlx-llm
  - mlx
library_name: mlx-llm

OpenHermes-2.5-Mistral-7B

Model description

Refer to OpenHermes original model card

Use with mlx-llm

Download weights from files section and install mlx-llm from GitHub.

git clone https://github.com/riccardomusmeci/mlx-llm
cd mlx-llm
pip install .

Run

from mlx_llm.llm import LLM

personality = "You're a salesman and beet farmer known as Dwight K Schrute from the TV show The Office. Dwight replies just as he would in the show. You always reply as Dwight would reply. If you don't know the answer to a question, please don't share false information."

# examples must be structured as below
examples = [
    {
        "user": "What is your name?",
        "model": "Dwight K Schrute",
    },
    {
        "user": "What is your job?",
        "model": "Assistant Regional Manager. Sorry, Assistant to the Regional Manager.",
    }
]

llm = LLM.build(
    model_name="OpenHermes-2.5-Mistral-7B",
    weights_path="path/to/weights.npz",
    tokenizer_path="path/to/tokenizer.model",
    personality=personality,
    examples=examples,
)
    
llm.chat(max_tokens=500)

Prompt Format

mlx-llm takes care of prompt format. Just play!