metadata

library_name: mlx
tags:
  - function calling
  - on-device language model
  - mlx
inference: false
space: false
spaces: false
language:
  - en
base_model: squeeze-ai-lab/TinyAgent-1.1B
pipeline_tag: text-generation
model-index:
  - name: TinyAgent-1.1B
    results: []

WannabeArchitect/TinyAgent-1.1B-MLX

This model WannabeArchitect/TinyAgent-1.1B-MLX was converted to MLX format from squeeze-ai-lab/TinyAgent-1.1B using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("WannabeArchitect/TinyAgent-1.1B-MLX")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)