abcorrea/random-v3
abcorrea/random-v3 is a 4 billion parameter language model fine-tuned from Qwen/Qwen3-4B-Thinking-2507. This model was trained using the TRL framework with Supervised Fine-Tuning (SFT) methods. It is designed for general text generation tasks, leveraging its 40960 token context length for comprehensive responses.
Loading preview...
Model Overview
abcorrea/random-v3 is a 4 billion parameter language model, specifically a fine-tuned variant of the Qwen/Qwen3-4B-Thinking-2507 base model. It has been developed using the TRL (Transformer Reinforcement Learning) framework, employing Supervised Fine-Tuning (SFT) as its training procedure. This model is equipped with a substantial context length of 40960 tokens, allowing it to process and generate longer, more coherent text sequences.
Key Capabilities
- Text Generation: Optimized for generating diverse and contextually relevant text based on user prompts.
- Fine-tuned Performance: Benefits from SFT training on a pre-existing Qwen3-4B model, enhancing its conversational and generative abilities.
- Extended Context: Supports a 40960 token context window, suitable for tasks requiring extensive input understanding or detailed output generation.
Training Details
The model's training leveraged the TRL framework (version 0.19.1) in conjunction with Transformers (4.52.1), Pytorch (2.7.0), Datasets (4.0.0), and Tokenizers (0.21.1). The training methodology was primarily Supervised Fine-Tuning (SFT), building upon the capabilities of its base model.