Overview

Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kv00.29 is an 8 billion parameter instruction-tuned model, building upon the meta-llama/Llama-3.1-8B-Instruct architecture. Developed by Neelectric, this model has undergone supervised fine-tuning (SFT) using the TRL framework.

Key Capabilities

• Mathematical Reasoning: The model is specifically fine-tuned on the Neelectric/OpenR1-Math-220k_extended_Llama3_4096toks dataset, enhancing its ability to understand and solve mathematical problems.
• Instruction Following: Inherits strong instruction-following capabilities from its base Llama-3.1-8B-Instruct model.
• Extended Context: Supports a context length of 32768 tokens, allowing for processing longer and more complex mathematical prompts or problem descriptions.

Training Details

The model was trained using the TRL library (version 0.27.0.dev0) with Transformers 4.57.3, Pytorch 2.9.0, Datasets 4.4.2, and Tokenizers 0.22.2. The training procedure focused on supervised fine-tuning to specialize the model for mathematical tasks.

Good For

• Applications requiring a specialized LLM for mathematical problem-solving.
• Educational tools that need to generate explanations or solutions for math problems.
• Research into fine-tuning large language models for specific domain expertise, particularly in mathematics.