This lora model is trained on a combination of 50MB datasets containing various conversations mainly from GPT4. The model shows a clear overfitting after 6 epochs. The base model is decapoda-research/llama-7b-hf You can use https://github.com/tloen/alpaca-lora to run it.
- Downloads last month
- 0
Unable to determine this model's library. Check the
docs
.