Hermes-3-Llama-3.2-3B-bf16/README.md

language, license, tags, base_model, widget, library_name, model-index

language	license	tags	base_model	widget	library_name	model-index
en	llama3	Llama-3 instruct finetune chatml gpt4 synthetic data distillation function calling json mode axolotl roleplaying chat mlx	NousResearch/Hermes-3-Llama-3.2-3B	example_title messages Hermes 3 role content system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. role content user Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.	transformers	name results Hermes-3-Llama-3.1-405B

mlx-community/Hermes-3-Llama-3.2-3B-bf16

The Model mlx-community/Hermes-3-Llama-3.2-3B-bf16 was converted to MLX format from NousResearch/Hermes-3-Llama-3.2-3B using mlx-lm version 0.20.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Hermes-3-Llama-3.2-3B-bf16")

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)