README.md

metadata

base_model:
  - CannaeAI/ReasoningLlama-Math-1B-IT
tags:
  - text-generation-inference
  - transformers
  - reasoning
  - math
  - thinking
  - conversational
  - llama
  - meta
license: apache-2.0
language:
  - en
datasets:
  - unsloth/OpenMathReasoning-mini

ReasoningLlama-Math-1B-IT-gguf

Model Description

This is a fine-tuned version of unsloth/Llama-3.2-1B on the unsloth/OpenMathReasoning-miniwhich is a small version of the nvidia/OpenMathReasoning dataset which was used to win the AIMO (AI Mathematical Olympiad) challenge!

• recommended settings for inference: min_p = 0.1 and temperature = 1.5 , Read this Tweet to understand why.
• License : apache-2.0
• Quantized from model : CannaeAI/ReasoningLlama-Math-1B-IT

Available Model files:

• ReasoningLlama-Math-1B.Q5_K_M.gguf
• ReasoningLlama-Math-1B.Q8_0.gguf
• ReasoningLlama-Math-1B.Q4_K_M.gguf

Ollama

An Ollama Modelfile is included for easy deployment.