Update README.md

README.md

@@ -1,6 +1,42 @@
 ---
+license: agpl-3.0
 library_name: peft
+tags:
+- not-for-all-audiences
 ---
+
+# Pippa-13b-qlora
+
+This is a repository of my Llama-2-13b Qlora checkpoints of the [PIPPA-13b-ShareGPT](https://huggingface.co/datasets/kingbri/PIPPA-ShareGPT) dataset.
+
+You can read more about the dataset on its relevant page. It's a ShareGPT reformat of the [PIPPA dataset](https://huggingface.co/datasets/PygmalionAI/PIPPA) by PygmalionAI. The reformat was done to allow for axolotl compatability.
+
+### Architecture
+
+- **Model Architecture**: Llama-2-13b
+- **Training Algorithm**: QLora
+- **Dataset Used**: PIPPA-ShareGPT (pippa_sharegpt_trimmed.jsonl)
+
+### Training Details
+
+- **Dataset**: [PIPPA-ShareGPT](https://huggingface.co/datasets/kingbri/PIPPA-ShareGPT)
+- **Datset type**: ShareGPT
+- **Training Parameters**: [See Here](https://gist.github.com/bdashore3/55ae04892f31609f2c3779c4a8a55408)
+- **Training Environment**: Axolotl
+- **sequence_len**: 4096
+
+## Notes
+
+This Qlora was produced as an experiment to see how the public version of PIPPA can affect a model. As a result, I have no idea if this lora is of great quality or absolute garbage.
+
+## Acknowledgments
+
+Thanks to:
+- PygmalionAI: The creators of the PIPPA dataset
+- Axolotl: Finetuning suite
+
+## Axolotl stuff
+
 ## Training procedure