ChesterProgrammer/V0.3
ChesterProgrammer/V0.3 is a 9 billion parameter Qwen3.5-based language model developed by ChesterProgrammer, fine-tuned from DreamFast/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark. This model was trained using LoRA with a context length of 1024 tokens, optimized for specific conversational or personality-driven tasks based on the Lucy_Personality dataset.
Loading preview...
ChesterProgrammer/V0.3 Model Overview
ChesterProgrammer/V0.3 is a 9 billion parameter language model, fine-tuned by ChesterProgrammer from the DreamFast/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark. This model leverages the Qwen3.5 architecture and was developed with a focus on efficient training methodologies.
Key Training Details
- Fine-tuning Method: LoRA (16-bit) with a rank of 8 and alpha of 16.
- Training Efficiency: Achieved 2x faster training using Unsloth and Huggingface's TRL library.
- Dataset: Trained on the Lucy_Personality dataset, comprising 398 samples.
- Context Length: Configured with a context length of 1024 tokens.
- Optimization: Utilized AdamW 8-bit optimizer with a learning rate of 0.0001 and a Cosine LR scheduler.
Intended Use Cases
Given its fine-tuning on a personality-focused dataset, ChesterProgrammer/V0.3 is likely suitable for applications requiring:
- Generating responses with specific personality traits.
- Engaging in conversational AI where character consistency is important.
- Exploring model behavior on smaller, specialized datasets.