lfm2.5-2.6b-toolcall-mlx-q8

LFM2.5-2.6B Tool-Call MLX (16-Bit Master)

This repository contains the unquantized 16-bit (Bfloat16) MLX version of Liquid AI's LFM2.5-2.6B, merged with a custom QLoRA adapter trained specifically for on-device tool and function calling on Apple Silicon and native iOS integration.

Model Details

• Base Model: LiquidAI/LFM2.5-2.6B
• Fine-Tuning: Custom QLoRA adapter trained for structured tool routing and argument normalization.
• Precision: 16-bit (Bfloat16 / Master Weights)
• Framework: Apple MLX (mlx-lm)

---

Capabilities & Strengths

• Argument Normalization: High accuracy in transforming natural, casual user phrasing (e.g., "call Mom at 6pm") into precise programmatic arguments (e.g., time='18:00').
• Multi-Tool Orchestration: Capable of executing parallel independent function calls in a single response.
• Full Fidelity: Retains the exact precision of the merged QLoRA training run before quantization steps.

---

How to Use (Python)

You can load and test this model locally using the mlx-lm package:

from mlx_lm import load, generate

model, tokenizer = load("hskyto/lfm2.5-2.6b-toolcall-mlx")

prompt = tokenizer.apply_chat_template(
    [
        {"role": "system", "content": "You are an assistant with local iOS tools."},
        {"role": "user", "content": "Remind me to call Mom at 6pm"}
    ],
    tokenize=False,
    add_generation_prompt=True
)

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