Add SGPT-125M-learntmean-nli

1_WeightedMeanPooling/config.json

@@ -0,0 +1,5 @@
+{
+  "word_embedding_dimension": 768,
+  "position_start": 0,
+  "num_positions": 75
+}

1_WeightedMeanPooling/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8874c1ad2a51f3ace5cbe24c54f4e2b3bd3e804db92db92bc4cb08953e21a1a
+size 1067

README.md

@@ -0,0 +1,89 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a None 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"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## 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})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 8807 with parameters:
+```
+{'batch_size': 64}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 880,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 881,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTNeoModel 
+  (1): WeightedMeanPooling()
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoModel"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.11.3",
+    "pytorch": "1.10.1"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,880,0.7874759629669823,0.7912446830570768,0.7903261342269166,0.7937779499298665,0.793451912598859,0.7971659469298812,0.6047788112816523,0.6507645985657873
+0,1760,0.8131803078100803,0.8217217521323321,0.8078740093837247,0.8136387056288685,0.80783684036113,0.8145862845746178,0.6442698777398019,0.6769324689376811
+0,2640,0.8205188607650769,0.8295576756894527,0.809619185876313,0.8164881399796352,0.8087770249430669,0.8164148498934699,0.6532800448682675,0.6845039439137265
+0,3520,0.8194023636022392,0.8291942305987777,0.8026114977298271,0.8097468417330873,0.8014032761561445,0.8094529536299162,0.6612855098370835,0.6945688013933999
+0,4400,0.8278999458091857,0.8370930561889419,0.8111320038675869,0.8180086766161624,0.808879055914931,0.8170175211278848,0.6760937280200618,0.7015204574363635
+0,5280,0.8281381038642194,0.8369509138876907,0.8051756334816669,0.8124593400462924,0.8028705531174375,0.8114328802631885,0.6819638474225186,0.708109243122145
+0,6160,0.8282860490892665,0.8380505641127632,0.8056595930718852,0.8127151391552065,0.8030974392778729,0.8112899442214865,0.6864753267136721,0.7133431150614978
+0,7040,0.8299474027656404,0.8385512601878364,0.8076509282307714,0.8144305140044854,0.8052765414613676,0.8130008421993484,0.6843023158951336,0.7116509270609606
+0,7920,0.83068475282831,0.83940890490782,0.8068064968525007,0.8135340881189486,0.8038602213322118,0.8116928430760436,0.6914461462348803,0.7144560233028373
+0,8800,0.8299367319536496,0.8391378193114882,0.8059099147634619,0.813011324412988,0.8027336665562144,0.8109457269020878,0.6892360704449959,0.7127091822396724
+0,-1,0.8299413185956964,0.8391453371102706,0.8058840017990108,0.8130046091058626,0.8027042937543123,0.8109357678204817,0.6892798410433907,0.7127213797569869

modules.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261c582ec054f7c7a021c7d427ac0a33418cf73e27ec9f11456a8c649b3955f2
+size 551190545

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 75,
+  "do_lower_case": false
+}

similarity_evaluation_sts-test_results.csv

@@ -0,0 +1,2 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+-1,-1,0.791277841042531,0.8008451549718872,0.7713262200294072,0.7736824259656975,0.7696089299758434,0.7737870864645463,0.58573209645255,0.5838254039153596

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}