Add SGPT-125M-lasttoken-nli

1_Pooling/config.json

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

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 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': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True})
+)
+```
+
+## 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": "4.12.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.12.3",
+    "pytorch": "1.10.0+cu113"
+  }
+}

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
+0,880,0.7551420032796191,0.7725067050207381,0.7588674756456201,0.7721572492461657,0.7773064881800951,0.7880601898381903,0.7111367122990645,0.7202382563316484
+0,1760,0.7713705055444604,0.7865558780364277,0.7790353439299134,0.788477197264167,0.7897109665652584,0.8002071667971283,0.7269170395342376,0.7344390081498672
+0,2640,0.7699562086103315,0.7874461039745826,0.7769244287055825,0.7879063516460753,0.7876963705060035,0.7993854348724125,0.7215068242710725,0.7334175216779879
+0,3520,0.780854345037378,0.7948026208002319,0.783402860069488,0.7942115662756436,0.7920039783858791,0.8039708653113827,0.7443724543110536,0.7543367140876786
+0,4400,0.7763847520694768,0.7911825693726021,0.781298418940732,0.7919251482138426,0.7895576136128409,0.8015714293723668,0.7379670002506049,0.7481425254136256
+0,5280,0.778784639696117,0.7920700397801209,0.7809632743182103,0.7905467877634046,0.7898230638656434,0.8012605234483808,0.7429248638347087,0.7533484037953371
+0,6160,0.7796314605780816,0.7944888227085405,0.7872542059442917,0.7969131341108013,0.7936556098109724,0.8056247775671218,0.739449983778461,0.7490313474276329
+0,7040,0.779484114814267,0.7936838594795055,0.7842686307456643,0.7949118265802351,0.7911904076878042,0.8035253418500725,0.7418311069418103,0.7532789695835953
+0,7920,0.7808217405823961,0.795174432463562,0.7862908021990734,0.7967789258264489,0.7934274408205118,0.805355161709273,0.7412633482903096,0.7521509794793086
+0,8800,0.7807963634201155,0.7947664812769661,0.7862579798542666,0.7966193954593038,0.7933823235976042,0.8054377400621869,0.741873832768781,0.7529905939392317
+0,-1,0.7808034042368943,0.7947718709606691,0.786263315248512,0.7966305376347383,0.7933838402605798,0.8054270407660142,0.7418980131934323,0.7529548270105705

modules.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a867856a56d56c886a9597d795c9855d633c3410a9ab671784aeddb9ee26080d
+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,-1,0.7040734792645174,0.7264413455860816,0.7266783760683704,0.7306313917617872,0.7432801579047458,0.7426151251572805,0.6679205280450954,0.6594317231269392

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"}