Update README.md

README.md

@@ -6,38 +6,19 @@ tags:
 - sentence-similarity
 ---
 
-# {MODEL_NAME}
-
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 4096 dimensional dense vector space and can be used for tasks like clustering or semantic search.
-
-<!--- Describe your model here -->
-
 ## Usage (Sentence-Transformers)
 
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
-
-```
-pip install -U sentence-transformers
-```
-
-Then you can use the model like this:
-
-```python
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+For usage instructions, refer to: https://github.com/Muennighoff/sgpt#asymmetric-semantic-search
 
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
+The model was trained with the command
+```bash
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 accelerate launch examples/training/ms_marco/train_bi-encoder_mnrl.py --model_name bigscience/bloom-7b1 --train_batch_size 32 --eval_batch_size 16 --freezenonbias --specb --lr 4e-4 --wandb --wandbwatchlog gradients --pooling weightedmean --gradcache --chunksize 8
 ```
 
-
-
 ## Evaluation Results
 
-<!--- Describe how your model was evaluated -->
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+`{"ndcgs": {"sgpt-bloom-7b1-msmarco": {"scifact": {"NDCG@10": 0.71824}, "nfcorpus": {"NDCG@10": 0.35748}, "arguana": {"NDCG@10": 0.47281}, "scidocs": {"NDCG@10": 0.18435}, "fiqa": {"NDCG@10": 0.35736}, "cqadupstack": {"NDCG@10": 0.3708525}, "quora": {"NDCG@10": 0.74655}, "trec-covid": {"NDCG@10": 0.82731}, "webis-touche2020": {"NDCG@10": 0.2365}}}`
 
 
 ## Training
@@ -50,6 +31,8 @@ The model was trained with the parameters:
 {'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
+The model uses BitFit, weighted-mean pooling & GradCache, for details see: https://arxiv.org/abs/2202.08904
+
 **Loss**:
 
 `sentence_transformers.losses.MultipleNegativesRankingLoss.MNRLGradCache` 
@@ -83,4 +66,11 @@ SentenceTransformer(
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->
+```bibtex
+@article{muennighoff2022sgpt,
+  title={SGPT: GPT Sentence Embeddings for Semantic Search},
+  author={Muennighoff, Niklas},
+  journal={arXiv preprint arXiv:2202.08904},
+  year={2022}
+}
+```