| license: other | |
| datasets: | |
| - tatsu-lab/alpaca | |
| LLaMA model finetuned using LoRA (1 epoch) on the Stanford Alpaca training data set and quantized to 4bit. | |
| Because this model contains the merged LLaMA weights it is subject to their license restrictions. |
| license: other | |
| datasets: | |
| - tatsu-lab/alpaca | |
| LLaMA model finetuned using LoRA (1 epoch) on the Stanford Alpaca training data set and quantized to 4bit. | |
| Because this model contains the merged LLaMA weights it is subject to their license restrictions. |