language, license, library_name, tags, pipeline_tag, model-index, base_model

language	license	library_name	tags	pipeline_tag	model-index	base_model
en	cc-by-nc-4.0	transformers	llama math reasoning fine-tuned fine-tuning	text-generation	name results Llama-3.1-8B-math-reasoning task dataset metrics type name text-generation Text Generation name type tulu3_mixture_math_reasoning custom name type value Training Loss loss 0.98	meta-llama/Llama-3.1-8B

Llama-3.1-8B Math Reasoning Model

Llama-3.1-8B SFT checkpoints for mathematical reasoning—artifacts of https://arxiv.org/abs/2509.11167.

Model Details

• Base model: Llama-3.1-8B
• Training dataset: tulu3_mixture_math_reasoning
• Learning rate: 5e-06
• Effective batch size: 128

Export Files

This repository includes export files for state averaging and other advanced techniques.