watt-tool-8B / README.md
leonnissen's picture
224de7c78d336015a1ec6c1cd05f8687d1bf7e2fc823501d490fc1435a7aec1a
905e72d verified
|
raw
history blame
876 Bytes
metadata
base_model: watt-ai/watt-tool-8B
language:
  - en
license: apache-2.0
tags:
  - function-calling
  - tool-use
  - llama
  - bfcl
  - mlx

mlx-community/watt-tool-8B

The Model mlx-community/watt-tool-8B was converted to MLX format from watt-ai/watt-tool-8B using mlx-lm version 0.20.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/watt-tool-8B")

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)