Uploaded model
- Developed by: kailasps
- License: apache-2.0
- Finetuned from model : meta-llama/Llama-2-7b-hf
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
The settings:
- The LoRA rank is 32
- Finetuned arround 80M params
- learning_rate = 1e-4
Unable to determine this model’s pipeline type. Check the
docs
.