Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v8
TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 21, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v8 is a 3.1 billion parameter instruction-tuned Qwen2.5 model developed by Smilesjs. This model is specifically fine-tuned for coding tasks, leveraging the Qwen2.5-Coder-3B-Instruct base. It was trained using Unsloth and Huggingface's TRL library, offering efficient performance for code generation and related applications.
Loading preview...
Overview
Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v8 is a 3.1 billion parameter language model, fine-tuned from the Qwen2.5-Coder-3B-Instruct base. Developed by Smilesjs, this model is optimized for coding-related tasks. It was trained efficiently using the Unsloth framework, which enables faster fine-tuning, and Huggingface's TRL library.
Key Capabilities
- Code Generation: Specialized for generating and understanding code, building upon the Qwen2.5-Coder architecture.
- Instruction Following: Designed to follow instructions effectively, making it suitable for interactive coding assistance.
- Efficient Training: Benefits from Unsloth's optimizations, suggesting a potentially well-tuned and performant model for its size.
Good For
- Developers seeking a compact yet capable model for code generation and programming assistance.
- Applications requiring instruction-tuned capabilities in a coding context.
- Environments where efficient model deployment and inference are crucial due to its 3.1B parameter count.