amylynn/Riverfish-Rocinante-12B-SFT
amylynn/Riverfish-Rocinante-12B-SFT is a 12 billion parameter Mistral-based causal language model developed by amylynn, fine-tuned from amylynn/Riverfish-Rocinante-12B. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. While primarily fine-tuned on specific content for personal usage, it retains general language capabilities.
Loading preview...
Model Overview
amylynn/Riverfish-Rocinante-12B-SFT is a 12 billion parameter language model developed by amylynn. It is a fine-tuned variant of the amylynn/Riverfish-Rocinante-12B model, built upon the Mistral architecture. The fine-tuning process leveraged Unsloth and Huggingface's TRL library, which facilitated a 2x faster training speed.
Key Characteristics
- Base Architecture: Mistral
- Parameter Count: 12 billion
- Training Efficiency: Utilizes Unsloth for accelerated fine-tuning.
- Context Length: Supports a context length of 32768 tokens.
Use Cases
This model was initially fine-tuned for specific personal content related to male-male interactions. However, due to its base as a general language model, it is expected to perform well on a variety of other general language tasks. Developers can explore its capabilities for diverse applications beyond its initial specialized training.