amylynn/Riverfish-Rocinante-12B-SFT-DPO
amylynn/Riverfish-Rocinante-12B-SFT-DPO is a 12 billion parameter Mistral-based language model developed by amylynn, fine-tuned from amylynn/Riverfish-Rocinante-12B-SFT. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It features a 32768 token context length and is primarily intended for general usage, with specific training on male-male content.
Loading preview...
Model Overview
amylynn/Riverfish-Rocinante-12B-SFT-DPO is a 12 billion parameter language model developed by amylynn. It is fine-tuned from amylynn/Riverfish-Rocinante-12B-SFT and built upon the Mistral architecture. A notable aspect of its development is the use of Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
Key Characteristics
- Parameter Count: 12 billion parameters.
- Context Length: Supports a context window of 32768 tokens.
- Training Efficiency: Leverages Unsloth for accelerated training.
- Specific Training Data: The model has been trained on male-male content, indicating a specialized focus in its fine-tuning data, though it is designed for general usage.
Intended Use Cases
This model is primarily intended for general usage, despite its specific training data. Developers might find it suitable for applications requiring a 12B parameter model with a large context window, especially if the specialized training data aligns with their specific content generation or understanding needs. Its efficient training methodology suggests a well-optimized model for deployment.