Model Card for Locutusque/Apollo-0.4-Llama-3.1-8B
SFT of Llama-3.1 8B. I was going to use DPO, but it made the model worse.
Model Details
Model Description
Fine-tuned Llama-3.1-8B on Locutusque/ApolloRP-2.0-SFT. Results in a good roleplaying language model, that isn't dumb.
- Developed by: Locutusque
- Model type: Llama3.1
- Language(s) (NLP): English
- License: Llama 3.1 Community License Agreement
Model Sources [optional]
Direct Use
RP/ERP, instruction following, conversation, etc
Bias, Risks, and Limitations
This model is completely uncensored - use at your own risk.
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Training Details
Training Data
The training data is cleaned from refusals, and "slop".
Training Hyperparameters
- Training regime: bf16 non-mixed precision
- Downloads last month
- 287
Inference API (serverless) is not available, repository is disabled.