New repo

.gitattributes

@@ -14,3 +14,4 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- causal-lm
+license:
+- CC-BY-SA-4.0
+---
+
+# TODO: Name of Model
+
+TODO: Description
+
+## Model Description
+TODO: Add relevant content
+
+(0) Base Transformer Type: RobertaModel
+
+(1) Pooling mean
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes more convenient when you have [sentence-transformers](https://github.com/UKPLab/sentence-transformers) 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"]
+
+model = SentenceTransformer(TODO)
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+## Usage (HuggingFace Transformers)
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+# The next step is optional if you want your own pooling function.
+# Max Pooling - Take the max value over time for every dimension. 
+def max_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    token_embeddings[input_mask_expanded == 0] = -1e9  # Set padding tokens to large negative value
+    max_over_time = torch.max(token_embeddings, 1)[0]
+    return max_over_time
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained(TODO)
+model = AutoModel.from_pretrained(TODO)
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt'))
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, max pooling.
+sentence_embeddings = max_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## TODO: Training Procedure
+
+## TODO: Evaluation Results
+
+## TODO: Citing & Authors

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/Users/osanseviero/.cache/torch/sentence_transformers/sbert.net_models_osanseviero_full-sentence-distillroberta2/",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bebbcc7ead5534be3f4dee3e5a1883e2a7e185f1c610256eaf5d804332fc4f9
+size 328477339

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4427e4ab70e3618994ff0caca2fc2243b17e65d25612fed844b986954d425d1
+size 328519167

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_special_tokens": false, "model_max_length": 512, "special_tokens_map_file": "/home/ukp-reimers/.cache/torch/transformers/4f4743e3f4fbeb763d116a0f2697f5e03117bd130711d90eaf795aeaeb7c4659.01d47f83d2e88283cc7f6be55eaef5d08d20297fc3bc1c1618ac15c35d1b97dd", "full_tokenizer_file": null, "name_or_path": "/Users/osanseviero/.cache/torch/sentence_transformers/sbert.net_models_osanseviero_full-sentence-distillroberta2/"}