Update README.md

README.md

@@ -1,3 +1,16 @@
+# LLARA-7B-Passage
+
+This model is fine-tuned from LLaMA-2-7B using LoRA and the embedding size is 4096.
+
+## Training Data
+
+The model is fine-tuned on the training split of [MS MARCO Passage Ranking](https://microsoft.github.io/msmarco/Datasets) datasets for 1 epoch. Please check our paper for details.
+
+## Usage
+
+Below is an example to encode a query and a passage, and then compute their similarity using their embedding.
+
+```python
 import torch
 from transformers import AutoModel, AutoTokenizer, LlamaModel
 
@@ -69,3 +82,6 @@ with torch.no_grad():
     # compute similarity score
     score = query_embedding @ passage_embeddings.T
     print(score)
+
+
+```