burnet01/qwen-rusty
The burnet01/qwen-rusty model is a 35.1 billion parameter causal language model, fine-tuned from unsloth/Qwen3.6-35B-A3B using the TRL framework. It features a 32,768 token context length, making it suitable for processing extensive inputs. This model is specifically optimized through supervised fine-tuning (SFT) to enhance its conversational and instruction-following capabilities.
Loading preview...
Model Overview
The burnet01/qwen-rusty model is a 35.1 billion parameter language model, derived from the unsloth/Qwen3.6-35B-A3B base model. It has been further refined through supervised fine-tuning (SFT) using the TRL (Transformer Reinforcement Learning) framework, indicating a focus on improving its instruction-following and conversational abilities. The model supports a substantial context length of 32,768 tokens, allowing it to handle complex and lengthy prompts.
Key Capabilities
- Instruction Following: Enhanced through SFT, making it adept at understanding and executing user instructions.
- Conversational AI: Optimized for engaging in more coherent and contextually relevant dialogues.
- Extended Context: Benefits from a 32,768 token context window, suitable for tasks requiring extensive input analysis or generation.
Training Details
The model was trained using the SFT method, leveraging the TRL library. This approach typically involves training on a dataset of high-quality instruction-response pairs to align the model's output with human preferences and instructions. The training environment utilized specific versions of key frameworks, including TRL 0.24.0, Transformers 5.5.0, PyTorch 2.11.0, Datasets 4.3.0, and Tokenizers 0.22.2.