Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.13

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 8, 2026Architecture:Transformer Cold

Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.13 is an 8 billion parameter instruction-tuned model developed by Neelectric, fine-tuned from Meta's Llama-3.1-8B-Instruct. It specializes in mathematical reasoning and problem-solving, leveraging a dedicated 220k-entry mathematical dataset. With a 32768 token context length, this model is optimized for tasks requiring robust mathematical understanding and generation.

Loading preview...

Model Overview

Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.13 is an 8 billion parameter language model, fine-tuned by Neelectric from the base meta-llama/Llama-3.1-8B-Instruct architecture. This model has undergone Supervised Fine-Tuning (SFT) using the Neelectric/OpenR1-Math-220k_all_Llama3_4096toks dataset, specifically designed for mathematical tasks.

Key Capabilities

  • Enhanced Mathematical Reasoning: Specialized fine-tuning on a large mathematical dataset improves its ability to understand and solve math problems.
  • Instruction Following: Retains the strong instruction-following capabilities of the Llama-3.1-8B-Instruct base model.
  • Extended Context: Supports a context length of 32768 tokens, beneficial for complex multi-step problems or detailed mathematical explanations.

Good For

  • Applications requiring accurate mathematical problem-solving.
  • Educational tools for generating explanations or solutions to math questions.
  • Research in mathematical reasoning within LLMs.

Training Details

The model was trained using the TRL framework, with specific versions of Transformers, PyTorch, Datasets, and Tokenizers as detailed in the original model card. The training process focused on SFT to imbue the model with its mathematical proficiency.

Finetunes
1 models