Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jan 19, 2026Architecture:Transformer Cold

Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01 is an 8 billion parameter instruction-tuned causal language model developed by Neelectric. It is a fine-tuned version of Meta's Llama-3.1-8B-Instruct, specifically optimized for mathematical reasoning tasks. This model leverages a 32768 token context length and is trained on the OpenR1-Math-220k_extended_Llama3_4096toks dataset, making it suitable for applications requiring strong mathematical problem-solving capabilities.

Loading preview...

Model Overview

Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01 is an 8 billion parameter instruction-tuned model, building upon the robust foundation of Meta's Llama-3.1-8B-Instruct. Developed by Neelectric, this model has been specifically fine-tuned using the TRL library to enhance its performance in mathematical reasoning.

Key Capabilities

  • Mathematical Reasoning: Specialized training on the Neelectric/OpenR1-Math-220k_extended_Llama3_4096toks dataset significantly improves its ability to handle mathematical problems.
  • Instruction Following: Retains the strong instruction-following capabilities of its base Llama-3.1-8B-Instruct model.
  • Extended Context: Benefits from the 32768 token context length of the Llama-3.1 series, allowing for processing longer and more complex mathematical prompts.

Training Details

The model underwent Supervised Fine-Tuning (SFT) using the TRL framework. The training process and metrics can be further explored via the associated Weights & Biases run.

When to Use This Model

This model is particularly well-suited for applications requiring accurate and robust mathematical problem-solving. It is an excellent choice for tasks such as:

  • Solving complex arithmetic and algebraic problems.
  • Generating explanations for mathematical concepts.
  • Assisting in educational tools focused on mathematics.