Model Overview

This model, goyalayus/wordle-lora-20260324-163252-sft_full_smoke, is a 0.8 billion parameter language model derived from the unsloth/Qwen3-0.6B base architecture. It has been specifically fine-tuned using the TRL (Transformer Reinforcement Learning) framework, employing a Supervised Fine-Tuning (SFT) procedure.

Key Characteristics

• Base Model: Fine-tuned from unsloth/Qwen3-0.6B.
• Training Method: Utilizes Supervised Fine-Tuning (SFT) with the TRL library.
• Context Length: Supports a context window of 32768 tokens.
• Framework Versions: Trained with TRL 0.24.0, Transformers 4.57.6, Pytorch 2.10.0, Datasets 4.3.0, and Tokenizers 0.22.2.

Intended Use

This model is suitable for various text generation tasks, particularly those requiring conversational responses, as demonstrated by the quick start example. Its fine-tuned nature suggests an optimization for generating coherent and contextually relevant text based on user prompts.