abcorrea/random-v2
abcorrea/random-v2 is a 4 billion parameter causal language model fine-tuned from Qwen/Qwen3-4B-Thinking-2507. This model was trained using SFT with the TRL framework, leveraging a 40960 token context length. It is designed for general text generation tasks, building upon the Qwen3 architecture.
Loading preview...
Overview
abcorrea/random-v2 is a 4 billion parameter language model, fine-tuned from the Qwen/Qwen3-4B-Thinking-2507 base model. It was developed using the TRL (Transformer Reinforcement Learning) framework, specifically employing Supervised Fine-Tuning (SFT) for its training procedure. The model supports a substantial context length of 40960 tokens, making it suitable for processing longer inputs and generating coherent, extended responses.
Key Capabilities
- Text Generation: Builds upon the Qwen3 architecture for general-purpose text generation.
- Extended Context: Benefits from a 40960 token context window, allowing for more detailed and context-aware interactions.
- Fine-tuned Performance: Utilizes SFT with the TRL library to enhance its performance for specific tasks, though the exact nature of the fine-tuning dataset is not specified in the README.
Good For
- Developers looking for a Qwen3-based model with a large context window.
- Applications requiring general text generation capabilities.
- Experimentation with models fine-tuned using the TRL framework.