README.md

metadata

library_name: transformers
base_model: DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning
datasets:
  - TeichAI/claude-4.5-opus-high-reasoning-250x
tags:
  - thinking
  - reasoning
  - finetune
  - creative
  - creative writing
  - fiction writing
  - plot generation
  - sub-plot generation
  - story generation
  - scene continue
  - storytelling
  - fiction story
  - science fiction
  - romance
  - all genres
  - story
  - writing
  - vivid prose
  - vivid writing
  - fiction
  - roleplaying
  - bfloat16
  - swearing
  - horror
  - unsloth
  - context 128k
  - mlx
  - mlx-my-repo
pipeline_tag: text-generation

alexgusevski/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning-mlx-3Bit

The Model alexgusevski/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning-mlx-3Bit was converted to MLX format from DavidAU/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/LFM2.5-1.2B-Instruct-Thinking-Claude-High-Reasoning-mlx-3Bit")

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)