初始化项目，由ModelHub XC社区提供模型

Model: Muennighoff/SGPT-1.3B-weightedmean-nli-bitfit
Source: Original Platform

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 2048,
+  "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 +1,72 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+---
+
+# SGPT-1.3B-weightedmean-nli-bitfit
+
+## Usage
+
+For usage instructions, refer to our codebase: https://github.com/Muennighoff/sgpt 
+
+## Evaluation Results
+
+For eval results, refer to the eval folder or our paper: https://arxiv.org/abs/2202.08904
+
+## 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: GPTNeoModel 
+  (1): Pooling({'word_embedding_dimension': 2048, '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
+
+```bibtex
+@article{muennighoff2022sgpt,
+  title={SGPT: GPT Sentence Embeddings for Semantic Search},
+  author={Muennighoff, Niklas},
+  journal={arXiv preprint arXiv:2202.08904},
+  year={2022}
+}
+```

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoModel"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "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": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.20.0.dev0",
+    "pytorch": "1.10.2"
+  }
+}

eval/SGPT-1.3B-weightedmean-nli-bitfit_weightedmean_layer-1_results_average_precision.json

@@ -0,0 +1,7 @@
+{
+    "askubuntu": 55.97,
+    "cqadupstack": 13.47,
+    "twitterpara": 73.06,
+    "scidocs": 72.77,
+    "avg": 53.817499999999995
+}

eval/SGPT-1.3B-weightedmean-nli-bitfit_weightedmean_layer-1_results_detailed.json

@@ -0,0 +1,66 @@
+{
+    "askubuntu": {
+        "map_askubuntu_title": 55.97,
+        "p@1_askubuntu_title": 52.69,
+        "p@5_askubuntu_title": 41.94,
+        "mrr_askubuntu_title": 68.08
+    },
+    "cqadupstack": {
+        "map@100_cqadupstack_unix": 11.88,
+        "ndcg@10_cqadupstack_unix": 13.74,
+        "map@100_cqadupstack_gaming": 29.28,
+        "ndcg@10_cqadupstack_gaming": 31.75,
+        "map@100_cqadupstack_wordpress": 4.34,
+        "ndcg@10_cqadupstack_wordpress": 5.12,
+        "map@100_cqadupstack_stats": 14.68,
+        "ndcg@10_cqadupstack_stats": 16.12,
+        "map@100_cqadupstack_tex": 8.04,
+        "ndcg@10_cqadupstack_tex": 8.43,
+        "map@100_cqadupstack_english": 14.07,
+        "ndcg@10_cqadupstack_english": 15.59,
+        "map@100_cqadupstack_programmers": 10.78,
+        "ndcg@10_cqadupstack_programmers": 11.23,
+        "map@100_cqadupstack_mathematica": 10.74,
+        "ndcg@10_cqadupstack_mathematica": 12.57,
+        "map@100_cqadupstack_physics": 16.04,
+        "ndcg@10_cqadupstack_physics": 17.58,
+        "map@100_cqadupstack_gis": 14.81,
+        "ndcg@10_cqadupstack_gis": 16.19,
+        "map@100_cqadupstack_webmasters": 9.84,
+        "ndcg@10_cqadupstack_webmasters": 10.36,
+        "map@100_cqadupstack_android": 17.19,
+        "ndcg@10_cqadupstack_android": 19.08,
+        "map@100_cqadupstack_avg": 13.47,
+        "ndcg@10_cqadupstack_avg": 14.81
+    },
+    "twitterpara": {
+        "ap_twitter_twitterurl": 75.43,
+        "spearman_twitter_twitterurl": 70.6,
+        "ap_twitter_pit": 70.69,
+        "spearman_twitter_pit": 55.71,
+        "ap_twitter_avg": 73.06,
+        "spearman_twitter_avg": 63.15
+    },
+    "scidocs": {
+        "map_scidocs_cite_euclidean": 70.1,
+        "ndcg_scidocs_cite_euclidean": 85.17,
+        "map_scidocs_cite_cosine": 70.1,
+        "ndcg_scidocs_cite_cosine": 85.17,
+        "map_scidocs_cocite_euclidean": 72.87,
+        "ndcg_scidocs_cocite_euclidean": 86.72,
+        "map_scidocs_cocite_cosine": 72.87,
+        "ndcg_scidocs_cocite_cosine": 86.72,
+        "map_scidocs_coview_euclidean": 74.95,
+        "ndcg_scidocs_coview_euclidean": 87.03,
+        "map_scidocs_coview_cosine": 74.95,
+        "ndcg_scidocs_coview_cosine": 87.03,
+        "map_scidocs_coread_euclidean": 73.15,
+        "ndcg_scidocs_coread_euclidean": 86.15,
+        "map_scidocs_coread_cosine": 73.15,
+        "ndcg_scidocs_coread_cosine": 86.15,
+        "map_scidocs_euclidean_avg": 72.77,
+        "ndcg_scidocs_euclidean_avg": 86.27,
+        "map_scidocs_cosine_avg": 72.77,
+        "ndcg_scidocs_cosine_avg": 86.27
+    }
+}

eval/quora.json

@@ -0,0 +1 @@
+{"SGPT-1.3B-weightedmean-nli-bitfit": {"quora": {"NDCG@1": 0.7423, "NDCG@3": 0.78936, "NDCG@5": 0.80689, "NDCG@10": 0.8233, "NDCG@100": 0.84217, "NDCG@1000": 0.84504}}}

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
+0,440,0.8486729726641167,0.8514738189278961,0.8515245319252214,0.8509027260070884,0.8540666757323956,0.8537290162137693,0.7630773568229123,0.7600358216618573
+0,880,0.860418177580361,0.8656263802961531,0.859274657391518,0.8610670106016408,0.8614574446998846,0.8635698806563004,0.775971737698288,0.7738330802938131
+0,1320,0.8646586808912774,0.8708047895637789,0.8600953037639533,0.8630166525165047,0.8623501857502746,0.8655507432332792,0.774750540444686,0.7725645527279972
+0,1760,0.8628892948335536,0.8689022188557769,0.8611001993825963,0.8627626879284295,0.8634677606209161,0.8653777840391851,0.7684411984607661,0.7660388115697093
+0,2200,0.8623264709023419,0.8684038857716583,0.8599140937391133,0.8623163529776595,0.8621011652259446,0.8648639001116789,0.7658429961100489,0.7630158219390278
+0,2640,0.8633934631804789,0.8700248299507874,0.8583066084846345,0.8610312177479946,0.8604516944303623,0.8632651971720137,0.7708747899267866,0.7695161449303083
+0,3080,0.864875512993908,0.8708072415227665,0.8570051556310841,0.8598815222390387,0.8592210627649711,0.8622960844035745,0.7675942152106912,0.765566539001796
+0,3520,0.8664358867199037,0.8717878560785026,0.8577414799031283,0.8608674339514554,0.8600366294063135,0.8633069107239323,0.7678182184536243,0.7655516315181986
+0,3960,0.8660615852729263,0.8715945872618516,0.8580011946328364,0.8608961297007961,0.8603219261222281,0.8635694785207915,0.7658642808961628,0.7634980873963996
+0,4400,0.8660032674381255,0.8715157046451364,0.8576564771305891,0.8606430352200829,0.8599938864592154,0.8633518022139872,0.7663838558727445,0.7645750276413869
+0,-1,0.865995009654422,0.8715109608696208,0.857644450885013,0.8606063092160902,0.8599858692389015,0.8633254320890273,0.7663788803033962,0.7645777465044731

eval/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,-1,0.8329852176094534,0.8386309954374512,0.8291196910761947,0.828296436242254,0.8302104318397378,0.8293978465982256,0.7205795699601987,0.7008266718943091

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 sha256:9e05f11a38a0abb8e97717b109e2d346a74cf1244e419ac5659416d9874487c8
+size 5363081601

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "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, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "errors": "replace", "pad_token": null, "add_bos_token": false, "tokenizer_class": "GPT2Tokenizer"}