metadata

library_name: transformers
license: apache-2.0
base_model: open-thoughts/OpenThinker3-7B
tags:
  - llama-factory
  - full
  - generated_from_trainer
  - mlx
  - mlx-my-repo
datasets:
  - open-thoughts/OpenThoughts3-1.2M
model-index:
  - name: OpenThinker3-7B
    results: []

mlx-community/OpenThinker3-7B-8bit

The Model mlx-community/OpenThinker3-7B-8bit was converted to MLX format from open-thoughts/OpenThinker3-7B using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/OpenThinker3-7B-8bit")

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)