Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kv00.32

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jan 18, 2026Architecture:Transformer Cold

Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kv00.32 is an 8 billion parameter instruction-tuned Llama-3.1 model developed by Neelectric. Fine-tuned on a specialized mathematical dataset, this model is optimized for reasoning and mathematical tasks. It leverages a 32768 token context length, making it suitable for complex problem-solving and detailed mathematical inquiries.

Loading preview...

Overview

Neelectric/Llama-3.1-8B-Instruct_SFT_Math-220kv00.32 is an 8 billion parameter instruction-tuned model based on Meta's Llama-3.1-8B-Instruct architecture. It has been specifically fine-tuned by Neelectric using Supervised Fine-Tuning (SFT) on the Neelectric/Replay_0.01.OpenR1-Math-220k_extended.wildguardmix.Llama3_4096toks dataset. This specialization aims to enhance its performance in mathematical reasoning and problem-solving.

Key Capabilities

  • Mathematical Reasoning: Optimized for handling mathematical queries and problems through fine-tuning on a dedicated math dataset.
  • Instruction Following: Inherits strong instruction-following capabilities from its base Llama-3.1-8B-Instruct model.
  • Context Handling: Supports a context length of 32768 tokens, allowing for processing longer and more complex mathematical problems or discussions.

Training Details

The model was trained using the TRL library, a framework for Transformer Reinforcement Learning, though the specific training method mentioned is SFT. The training utilized various updated framework versions including TRL 0.28.0.dev0 and Transformers 4.57.6.

Good For

  • Applications requiring robust mathematical problem-solving.
  • Educational tools for math assistance.
  • Research in AI for mathematical reasoning.