abcorrea/sok-v5
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Nov 8, 2025Architecture:Transformer Cold
abcorrea/sok-v5 is a 4 billion parameter language model fine-tuned from Qwen/Qwen3-4B-Thinking-2507. This model was trained using the TRL framework, focusing on specific instruction-following capabilities. It is designed for general text generation tasks, leveraging the Qwen3 architecture for efficient performance.
Loading preview...
Model Overview
abcorrea/sok-v5 is a 4 billion parameter language model, fine-tuned from the base model Qwen/Qwen3-4B-Thinking-2507. This model has undergone supervised fine-tuning (SFT) using the TRL library, a framework developed for Transformer Reinforcement Learning.
Key Capabilities
- Instruction Following: Optimized through SFT to respond to user prompts and generate coherent text based on instructions.
- Text Generation: Capable of generating diverse text outputs, suitable for various conversational or creative tasks.
- Qwen3 Architecture: Benefits from the underlying Qwen3 architecture, known for its efficiency and performance in its size class.
Training Details
The model was trained using the SFT method, leveraging specific versions of popular machine learning frameworks:
- TRL: 0.19.1
- Transformers: 4.52.1
- Pytorch: 2.7.0
- Datasets: 4.0.0
- Tokenizers: 0.21.1
Good For
- Developers looking for a fine-tuned Qwen3-based model for text generation.
- Applications requiring instruction-tuned responses from a 4B parameter model.
- Experimentation with models trained using the TRL framework.