SaketR1/uncertainty-sft-2
SaketR1/uncertainty-sft-2 is a 2.3 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen3.5-2B using the TRL framework. This model is designed for general text generation tasks, leveraging its base architecture for efficient performance. It offers a 32,768 token context length, making it suitable for processing moderately long inputs and generating coherent responses.
Loading preview...
Model Overview
SaketR1/uncertainty-sft-2 is a 2.3 billion parameter language model, fine-tuned from the Qwen/Qwen3.5-2B architecture. The fine-tuning process utilized the TRL library, a framework for Transformer Reinforcement Learning, specifically employing Supervised Fine-Tuning (SFT).
Key Capabilities
- General Text Generation: Capable of generating human-like text based on given prompts.
- Instruction Following: Fine-tuned to understand and respond to user instructions.
- Moderate Context Handling: Supports a context length of 32,768 tokens, allowing for processing and generating longer sequences of text.
Training Details
The model was trained using the SFT method within the TRL framework. The development environment included TRL 1.6.0, Transformers 5.13.0.dev0, Pytorch 2.11.0+cu128, Datasets 5.0.0, and Tokenizers 0.22.2.
Use Cases
This model is suitable for various applications requiring text generation, such as chatbots, content creation, summarization, and question-answering, particularly where a balance between model size and context handling is desired.