AryanK123/Llama-3.2-1B-Instruct_SFT_Math-220kv00.04

TEXT GENERATIONPricing:Input $0.108 / Output $0.804Concurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 4, 2026Architecture:Transformer Featherless Exclusive Cold

AryanK123/Llama-3.2-1B-Instruct_SFT_Math-220kv00.04 is a 1 billion parameter instruction-tuned causal language model, fine-tuned from meta-llama/Llama-3.2-1B-Instruct. This model specializes in mathematical reasoning and problem-solving, having been trained on the OpenR1-Math-220k_extended_Llama3_4096toks dataset. It leverages a 32768 token context length and is optimized for tasks requiring strong mathematical capabilities.

Loading preview...

Overview

This model, AryanK123/Llama-3.2-1B-Instruct_SFT_Math-220kv00.04, is a specialized 1 billion parameter instruction-tuned language model. It is built upon the meta-llama/Llama-3.2-1B-Instruct architecture and has been specifically fine-tuned for mathematical tasks. The training utilized the Neelectric/OpenR1-Math-220k_extended_Llama3_4096toks dataset, enhancing its proficiency in mathematical reasoning and problem-solving.

Key Capabilities

  • Mathematical Reasoning: Enhanced performance on math-related queries due to specialized SFT training.
  • Instruction Following: Retains instruction-following capabilities from its base Llama-3.2-1B-Instruct model.
  • Context Handling: Supports a substantial context length of 32768 tokens, beneficial for complex problems.

Training Details

The model was trained using the TRL (Transformer Reinforcement Learning) library, indicating a supervised fine-tuning (SFT) approach. The training process is trackable via Weights & Biases, providing transparency into its development. This focused training on a math-centric dataset differentiates it from general-purpose instruction-tuned models of similar size.

Good For

  • Applications requiring accurate mathematical problem-solving.
  • Educational tools for math assistance.
  • Generating or evaluating mathematical explanations and solutions.