add merged models gtr

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+spiece.model filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+config.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+sentence-transformers filter=lfs diff=lfs merge=lfs -text
+modules.json filter=lfs diff=lfs merge=lfs -text
+special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,51 @@
----
-license: apache-2.0
-language:
-- en
-tags:
-- dense retrieval
----
-
-This model checkpoint is identical to https://huggingface.co/sentence-transformers/gtr-t5-base.
-But include the model's dense layer.
-
-Check the model class detail at: ...
+---
+pipeline_tag: sentence-similarity
+language: en
+license: apache-2.0
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+---
+
+# sentence-transformers/gtr-t5-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space. The model was specifically trained for the task of sematic search.
+
+This model was converted from the Tensorflow model [gtr-base-1](https://tfhub.dev/google/gtr/gtr-base/1) to PyTorch. When using this model, have a look at the publication: [Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899). The tfhub model and this PyTorch model can produce slightly different embeddings, however, when run on the same benchmarks, they produce identical results.
+
+The model uses only the encoder from a T5-base model. The weights are stored in FP16.  
+
+
+## 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"]
+
+model = SentenceTransformer('sentence-transformers/gtr-t5-base')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+The model requires sentence-transformers version 2.2.0 or newer.
+
+## Evaluation Results
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/gtr-t5-base)
+
+
+
+## Citing & Authors
+
+If you find this model helpful, please cite the respective publication:
+[Large Dual Encoders Are Generalizable Retrievers](https://arxiv.org/abs/2112.07899)

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c505a1fdbd38cf5f6d3ad747f9338345d41a0dc029b305f1525c2bef839d032
+size 1381

modules.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41251094dfd3e7ff81a85ba97b3f4788df47e4039f1bc5037575b43c028beb40
+size 461

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0115a9109a9809523f1ef8d28756657458ececb829fa9faba410b42f1e12409
+size 221653921

sentence-transformers/.gitattributes

@@ -0,0 +1,5 @@
+config_sentence_transformers.json filter=lfs diff=lfs merge=lfs -text
+convert-gtr.ipynb filter=lfs diff=lfs merge=lfs -text
+convert_to_fp16.py filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+sentence_bert_config.json filter=lfs diff=lfs merge=lfs -text

sentence-transformers/config_sentence_transformers.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f631e4bd49910419948c5e9134ab07e0d63b22b8cebbe6875f99a0712bcadd4d
+size 122

sentence-transformers/convert-gtr.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665ac3935da4e9b2bc7ebd3355201ca4484b5777b44aa9351c9eb798dd4bb4bb
+size 90620

sentence-transformers/convert_to_fp16.py

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbd5bfc49c82ef29c7b91f00562069f11551b024782fc4260609329addedfd3
+size 198

sentence-transformers/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd78a39e92ec5e96213ad3284d95360ba13c020bbda0841479b369612b19964c
+size 219303530

sentence-transformers/sentence_bert_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8e29d6dcb61b611b7d3fdd2982c4524e6ad985959fa7194eacfb655a8d0d51
+size 53

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4720c0fddbe4c5991334f85ad7073d9bd0a294a8ba4641a2f8dab614ca825949
+size 1786

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd4249b57e28dda22219397c091a4a11655c537e0d8a9b5e2efcf43f39c8773
+size 1387554

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6973652f30c2c8359a70d8fe41f9af4f13b3225d9520dbecfe0b7f0c69f997f3
+size 1923