Add SGPT-125M-mean-nli-linear5

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.GELU"}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab58ee7c0bf4ebb6a6c66b3907aef60dcc3662952df1393b01723c4dd0fb50ea
+size 2363431

3_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.GELU"}

3_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdcc7e501da47fb2ee1297506d5cd1a96d3bce3b91589461b3349b5cfb62f80d
+size 2363431

4_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.GELU"}

4_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611bfb930f316f7517bcef08cb7df35d2062feb5890533c41b0464732f979abb
+size 2363431

5_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.GELU"}

5_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc11027db566a4d3dc2ccf9f55e68d1930be618e219bc6e090bff3532644663a
+size 2363431

6_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 768, "bias": true, "activation_function": "torch.nn.modules.activation.GELU"}

6_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649980f85e7cc80814d98cdf98494cfd69dddf05b102e4e519a2c4efe12e1f4e
+size 2363431

README.md

@@ -0,0 +1,94 @@
+---
+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 768 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): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.GELU'})
+  (3): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.GELU'})
+  (4): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.GELU'})
+  (5): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.GELU'})
+  (6): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.GELU'})
+)
+```
+
+## 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
+0,880,0.6793242897830243,0.6800051116275396,0.6526675304698322,0.6598914874266282,0.6523759012817913,0.6596549908221383,0.37758613161811344,0.44107892538971527
+0,1760,0.7093062659759418,0.7043392262855407,0.6799424742385566,0.6871311628086488,0.679709965760185,0.686909064790608,0.4244807707330064,0.489454058418039
+0,2640,0.7162510204173811,0.7108099478329052,0.6844751159621512,0.6902131311277189,0.6843642132691589,0.6900856150254838,0.4430006769070316,0.49415192642877115
+0,3520,0.7210577333102874,0.7159412485270954,0.6874901591743661,0.693434015639469,0.6875126171641188,0.6936410018207312,0.45731448945063213,0.5199390563243889
+0,4400,0.7279170676663442,0.7217689927624069,0.6918732703073953,0.6971102070618418,0.6917278226947479,0.6970824988576667,0.45420687165035545,0.5189615022689855
+0,5280,0.7260344818186505,0.720721312324089,0.6921883942481113,0.6972724171381975,0.6921449258154431,0.6971027942453383,0.43819063915065287,0.5029727634769791
+0,6160,0.7286999102843462,0.7228504098788112,0.6939166076911062,0.6994848783615378,0.6937150393058567,0.6991998971160589,0.445240349764503,0.5095797004208383
+0,7040,0.7302858437234605,0.725494459746203,0.694175642980331,0.6995536927338825,0.6937733393621677,0.6991565696840228,0.439262522665688,0.5065563833877958
+0,7920,0.7314337586011384,0.7268544909338852,0.6942073318019882,0.6996691145217213,0.6938620780761877,0.6992384398472841,0.44088081789557454,0.5113894614562506
+0,8800,0.7316399822010149,0.7275473603861525,0.6938081719844009,0.699432422187559,0.6934701320652052,0.698900686945158,0.43536164213762274,0.5046829247995284
+0,-1,0.7316436973142261,0.7275333401568148,0.6938119379020147,0.6994414880301143,0.6934733474552642,0.6989065292074504,0.4353497873382448,0.5046755102036641

modules.json

@@ -0,0 +1,44 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 5,
+    "name": "5",
+    "path": "5_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 6,
+    "name": "6",
+    "path": "6_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4119de5997c833c7566dc4766cfd1ce0fcafab88f327adf0dbd85e41f03e3c
+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,-1,0.67010540977066,0.6281656744516964,0.6151881660970145,0.5880977577692394,0.6156838702005203,0.5883481650395049,0.3694855758671593,0.4361936325224468

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"}