README.md

---
datasets:
- ash001/arxiv-abstract
base_model:
- meta-llama/Llama-2-70b-chat-hf
---
# Model Card for prompts-save-70b

This model comprises prompt embeddings fine-tuned on [LLaMA 2 70B](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) using prompt tuning with the Petals framework.

This model was fine-tuned using the [arxiv-abstract-dataset](https://huggingface.co/datasets/ash001/arxiv-abstract).

For explaining more on how we did this, please check out this [article](https://medium.com/@kannansarat9/part-2-prompt-tuning-llama-2-70b-using-petals-model-parallelism-over-the-internet-89cdee667840)!