Add SGPT-6.1B-weightedmean-nli-bitfit

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 4096,
+  "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": true,
+  "pooling_mode_lasttoken": false
+}

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 4096 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 93941 with parameters:
+```
+{'batch_size': 6}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 9394,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 0.0001
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 9395,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTJModel 
+  (1): Pooling({'word_embedding_dimension': 4096, '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': True, 'pooling_mode_lasttoken': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

added_tokens.json

@@ -0,0 +1 @@
+{"<|extratoken_41|>": 50297, "<|extratoken_109|>": 50365, "<|extratoken_17|>": 50273, "<|extratoken_22|>": 50278, "<|extratoken_137|>": 50393, "<|extratoken_131|>": 50387, "<|extratoken_130|>": 50386, "<|extratoken_52|>": 50308, "<|extratoken_96|>": 50352, "<|extratoken_70|>": 50326, "<|extratoken_19|>": 50275, "<|extratoken_54|>": 50310, "<|extratoken_15|>": 50271, "<|extratoken_101|>": 50357, "<|extratoken_37|>": 50293, "<|extratoken_98|>": 50354, "<|extratoken_57|>": 50313, "<|extratoken_69|>": 50325, "<|extratoken_1|>": 50257, "<|extratoken_18|>": 50274, "<|extratoken_87|>": 50343, "<|extratoken_81|>": 50337, "<|extratoken_21|>": 50277, "<|extratoken_72|>": 50328, "<|extratoken_8|>": 50264, "<|extratoken_83|>": 50339, "<|extratoken_53|>": 50309, "<|extratoken_123|>": 50379, "<|extratoken_59|>": 50315, "<|extratoken_65|>": 50321, "<|extratoken_28|>": 50284, "<|extratoken_90|>": 50346, "<|extratoken_108|>": 50364, "<|extratoken_30|>": 50286, "<|extratoken_84|>": 50340, "<|extratoken_88|>": 50344, "<|extratoken_67|>": 50323, "<|extratoken_94|>": 50350, "<|extratoken_86|>": 50342, "<|extratoken_7|>": 50263, "<|extratoken_4|>": 50260, "<|extratoken_48|>": 50304, "<|extratoken_112|>": 50368, "<|extratoken_14|>": 50270, "<|extratoken_100|>": 50356, "<|extratoken_116|>": 50372, "<|extratoken_25|>": 50281, "<|extratoken_118|>": 50374, "<|extratoken_139|>": 50395, "<|extratoken_73|>": 50329, "<|extratoken_80|>": 50336, "<|extratoken_74|>": 50330, "<|extratoken_119|>": 50375, "<|extratoken_128|>": 50384, "<|extratoken_133|>": 50389, "<|extratoken_63|>": 50319, "<|extratoken_47|>": 50303, "<|extratoken_132|>": 50388, "<|extratoken_12|>": 50268, "<|extratoken_127|>": 50383, "<|extratoken_6|>": 50262, "<|extratoken_71|>": 50327, "<|extratoken_35|>": 50291, "<|extratoken_2|>": 50258, "<|extratoken_143|>": 50399, "<|extratoken_44|>": 50300, "<|extratoken_45|>": 50301, "<|extratoken_68|>": 50324, "<|extratoken_138|>": 50394, "<|extratoken_58|>": 50314, "<|extratoken_31|>": 50287, "<|extratoken_49|>": 50305, "<|extratoken_99|>": 50355, "<|extratoken_39|>": 50295, "<|extratoken_97|>": 50353, "<|extratoken_16|>": 50272, "<|extratoken_125|>": 50381, "<|extratoken_79|>": 50335, "<|extratoken_43|>": 50299, "<|extratoken_46|>": 50302, "<|extratoken_62|>": 50318, "<|extratoken_75|>": 50331, "<|extratoken_33|>": 50289, "<|extratoken_26|>": 50282, "<|extratoken_38|>": 50294, "<|extratoken_82|>": 50338, "<|extratoken_129|>": 50385, "<|extratoken_10|>": 50266, "<|extratoken_117|>": 50373, "<|extratoken_121|>": 50377, "<|extratoken_111|>": 50367, "<|extratoken_92|>": 50348, "<|extratoken_85|>": 50341, "<|extratoken_115|>": 50371, "<|extratoken_142|>": 50398, "<|extratoken_27|>": 50283, "<|extratoken_95|>": 50351, "<|extratoken_91|>": 50347, "<|extratoken_77|>": 50333, "<|extratoken_32|>": 50288, "<|extratoken_20|>": 50276, "<|extratoken_60|>": 50316, "<|extratoken_24|>": 50280, "<|extratoken_3|>": 50259, "<|extratoken_36|>": 50292, "<|extratoken_114|>": 50370, "<|extratoken_105|>": 50361, "<|extratoken_136|>": 50392, "<|extratoken_55|>": 50311, "<|extratoken_141|>": 50397, "<|extratoken_124|>": 50380, "<|extratoken_103|>": 50359, "<|extratoken_76|>": 50332, "<|extratoken_113|>": 50369, "<|extratoken_34|>": 50290, "<|extratoken_40|>": 50296, "<|extratoken_140|>": 50396, "<|extratoken_13|>": 50269, "<|extratoken_126|>": 50382, "<|extratoken_106|>": 50362, "<|extratoken_5|>": 50261, "<|extratoken_42|>": 50298, "<|extratoken_23|>": 50279, "<|extratoken_56|>": 50312, "<|extratoken_102|>": 50358, "<|extratoken_104|>": 50360, "<|extratoken_110|>": 50366, "<|extratoken_122|>": 50378, "<|extratoken_89|>": 50345, "<|extratoken_78|>": 50334, "<|extratoken_135|>": 50391, "<|extratoken_134|>": 50390, "<|extratoken_64|>": 50320, "<|extratoken_11|>": 50267, "<|extratoken_61|>": 50317, "<|extratoken_29|>": 50285, "<|extratoken_107|>": 50363, "<|extratoken_120|>": 50376, "<|extratoken_66|>": 50322, "<|extratoken_51|>": 50307, "<|extratoken_9|>": 50265, "<|extratoken_93|>": 50349, "<|extratoken_50|>": 50306}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "EleutherAI/gpt-j-6B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_ctx": 2048,
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary": true,
+  "rotary_dim": 64,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 50400
+}

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
+0,9394,0.8667856977815679,0.8683593379338206,0.8295642056627444,0.8363884778489342,0.8297954592955538,0.8366900215048471,0.7273903009136995,0.7450463171103514
+0,18788,0.8689264665368805,0.8730176667630773,0.8172574760443659,0.826681430241987,0.8174496565604266,0.826906202638698,0.7251340335813794,0.7494408699573307
+0,28182,0.869626405230146,0.8746725718167937,0.8117418430598462,0.8233372731358232,0.8119217193234098,0.823456339054079,0.7156090695589337,0.745283587736306
+0,37576,0.8721744243944177,0.876376158288002,0.8092960874069344,0.8208668853143776,0.8093684853534436,0.8207676236802162,0.7097850859694168,0.740015795854084
+0,46970,0.8685973670816101,0.8735217151527351,0.7994400795758065,0.8141999661345705,0.7995773482164976,0.8142136245069611,0.7048865353912706,0.7374451001344114
+0,56364,0.8670753990703621,0.8709915852972844,0.7950924657883385,0.8090357828645908,0.7952413489633985,0.809093359416678,0.7069143199588939,0.7401687532547431
+0,65758,0.8680677166487298,0.872010642938237,0.7910244128044988,0.804831925878411,0.7911861404707381,0.8049586839727801,0.707650896879289,0.7411846721034997
+0,75152,0.8671966956114382,0.8714106816711714,0.7916891431485983,0.8053307393890206,0.7918070185130721,0.8054928629924096,0.7031691980078598,0.7365621493487114
+0,84546,0.8661075138525474,0.8700145205677993,0.7871377350626456,0.8006476471975226,0.7872536565066849,0.8006875885061543,0.7032941404752215,0.7383746132297418
+0,93940,0.8669285782887518,0.8708788467855191,0.7882799653262015,0.8018519610168285,0.7884034221151361,0.8020195609532438,0.7023297544615408,0.7380559226189177
+0,-1,0.8669294815942044,0.8708691243588981,0.7882804405199759,0.801845053715687,0.7884042369770401,0.8020289186109306,0.7023314160887122,0.7380687909551775

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 sha256:51b02dde1fc8932ddb8abb409f7afb449bf889d7881f36eab6c4fab19dbd88d2
+size 23495139247

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,-1,0.8545703732519089,0.8628560963867633,0.7953746046954051,0.803146877550554,0.7952608148592852,0.8032415734370247,0.5954996603580655,0.6054272543624561

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-j-6B", "tokenizer_class": "GPT2Tokenizer"}