ned1313/sft-gsm8k
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 12, 2026Architecture:Transformer Featherless Exclusive Cold
The ned1313/sft-gsm8k model is a fine-tuned version of Qwen/Qwen3-0.6B-Base, a 0.8 billion parameter language model. It has been specifically trained using Supervised Fine-Tuning (SFT) with the TRL library. This model is optimized for mathematical reasoning and problem-solving tasks, particularly those found in the GSM8K dataset. Its compact size and specialized training make it suitable for efficient deployment in applications requiring strong arithmetic and logical capabilities.
Loading preview...
Overview
This model, ned1313/sft-gsm8k, is a specialized fine-tuned variant of the Qwen3-0.6B-Base architecture, developed by ned1313. With approximately 0.8 billion parameters, it leverages the robust foundation of the Qwen3 series.
Key Capabilities
- Mathematical Reasoning: The model has undergone Supervised Fine-Tuning (SFT) specifically targeting the GSM8K dataset, indicating a strong focus on arithmetic and multi-step mathematical problem-solving.
- Efficient Deployment: Its relatively small parameter count (0.8B) makes it suitable for applications where computational resources are a consideration, allowing for faster inference compared to larger models.
- TRL Framework: Training was conducted using the TRL library, a framework designed for transformer reinforcement learning, suggesting a structured approach to fine-tuning.
Good For
- Educational Tools: Developing AI assistants for math homework or problem-solving in educational settings.
- Automated Problem Solving: Integrating into systems that require automated solutions to quantitative problems.
- Research in Mathematical LLMs: Serving as a base for further experimentation and fine-tuning on mathematical reasoning tasks.