lewtun/Qwen3-4B-Capybara-SFT
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 18, 2026Architecture:Transformer Cold
lewtun/Qwen3-4B-Capybara-SFT is a 4 billion parameter causal language model, fine-tuned from Qwen/Qwen3-4B-Base using Supervised Fine-Tuning (SFT) with TRL. This model is designed for general text generation tasks, leveraging the Qwen3 architecture for efficient performance. It offers a 32768 token context length, making it suitable for applications requiring processing of longer inputs and generating coherent, extended responses.
Loading preview...
Model Overview
lewtun/Qwen3-4B-Capybara-SFT is a 4 billion parameter language model, fine-tuned from the Qwen/Qwen3-4B-Base architecture. This model was developed using Supervised Fine-Tuning (SFT) via the TRL library, indicating an optimization for instruction-following and conversational capabilities.
Key Capabilities
- Text Generation: Excels at generating coherent and contextually relevant text based on provided prompts.
- Instruction Following: Fine-tuned with SFT, suggesting improved ability to follow specific instructions and generate desired outputs.
- Qwen3 Architecture: Benefits from the underlying Qwen3 base model's efficiency and performance characteristics.
- Extended Context: Supports a context length of 32768 tokens, allowing for processing and generating longer sequences of text.
Good For
- General-purpose chatbots: Its SFT training makes it suitable for interactive conversational agents.
- Content creation: Can be used for generating various forms of text, from creative writing to informative responses.
- Prototyping LLM applications: A 4B parameter model offers a balance of performance and computational efficiency for development and experimentation.