README.md

metadata

base_model: krory/GenBook-Deepseek-R1.Llama-8B
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
  - mlx
  - mlx-my-repo
license: apache-2.0
language:
  - es
  - en

nhe-ai/GenBook-Deepseek-R1.Llama-8B-Q3-mlx

The Model nhe-ai/GenBook-Deepseek-R1.Llama-8B-Q3-mlx was converted to MLX format from krory/GenBook-Deepseek-R1.Llama-8B using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("nhe-ai/GenBook-Deepseek-R1.Llama-8B-Q3-mlx")

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)