minh9212/qwen3-0.6b-SFTchat_math

TEXT GENERATIONConcurrency Cost:1Model Size:0.8BQuant:BF16Ctx Length:32kPublished:May 9, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The minh9212/qwen3-0.6b-SFTchat_math is a 0.8 billion parameter Qwen3-based causal language model developed by minh9212. Fine-tuned from unsloth/Qwen3-0.6B-unsloth-bnb-4bit, this model is optimized for chat and mathematical tasks. It was trained using Unsloth and Huggingface's TRL library, offering a 32768 token context length.

Loading preview...

Overview

The minh9212/qwen3-0.6b-SFTchat_math is a 0.8 billion parameter language model based on the Qwen3 architecture. Developed by minh9212, this model is a fine-tuned version of unsloth/Qwen3-0.6B-unsloth-bnb-4bit and is specifically designed for chat interactions and mathematical problem-solving. It leverages the Unsloth library for accelerated training, achieving a 2x speed improvement, alongside Huggingface's TRL library.

Key Capabilities

  • Chat-optimized: Designed for conversational AI applications.
  • Mathematical proficiency: Fine-tuned to handle mathematical tasks.
  • Efficient Training: Utilizes Unsloth for faster training, making it resource-efficient.
  • Context Length: Supports a substantial context window of 32768 tokens.

Good For

  • Applications requiring a compact yet capable model for general chat.
  • Scenarios where mathematical reasoning and problem-solving are key.
  • Developers looking for a model trained with efficient methods like Unsloth.