metadata
license: mit
library_name: transformers
datasets:
- FractalAIResearch/Fathom-V0.4-SFT-Shortest-Chains
- FractalAIResearch/Fathom-V0.6-Iterative-Curriculum-Learning
base_model: FractalAIResearch/Fathom-R1-14B
tags:
- mlx
cnfusion/Fathom-R1-14B-mlx-4Bit
The Model cnfusion/Fathom-R1-14B-mlx-4Bit was converted to MLX format from FractalAIResearch/Fathom-R1-14B using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("cnfusion/Fathom-R1-14B-mlx-4Bit")
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)