Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.16

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 14, 2026Architecture:Transformer Featherless Exclusive Cold

Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.16 is a fine-tuned version of Meta's Llama-3.1-8B-Instruct model. Developed by Neelectric, this model has been specifically trained on the OpenR1-Math-220k_all_Llama3_4096toks dataset. It is optimized for mathematical and reasoning tasks, leveraging supervised fine-tuning (SFT) to enhance its performance in these domains. This model is suitable for applications requiring improved accuracy on math-related problems.

Loading preview...

Model Overview

Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.16 is a specialized language model derived from Meta's Llama-3.1-8B-Instruct. This model has undergone supervised fine-tuning (SFT) using the Neelectric/OpenR1-Math-220k_all_Llama3_4096toks dataset, which is designed to enhance its capabilities in mathematical reasoning and problem-solving.

Key Capabilities

  • Enhanced Mathematical Reasoning: Specifically fine-tuned on a dedicated math dataset to improve performance on quantitative tasks.
  • Instruction Following: Retains the strong instruction-following abilities of its base Llama-3.1-8B-Instruct model.
  • Supervised Fine-Tuning (SFT): Utilizes SFT with the TRL framework to adapt the base model for specialized mathematical contexts.

Training Details

The model was trained using the TRL framework, with specific versions including TRL 1.1.0.dev0, Transformers 4.57.6, Pytorch 2.9.0, Datasets 5.0.1, and Tokenizers 0.22.2. This fine-tuning process aims to make the model more robust and accurate for tasks requiring numerical and logical understanding.

Recommended Use Cases

This model is particularly well-suited for applications that involve:

  • Solving mathematical problems.
  • Generating explanations for mathematical concepts.
  • Assisting with quantitative analysis and reasoning tasks.