初始化项目，由ModelHub XC社区提供模型

Model: Muennighoff/SGPT-2.7B-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": 2560,
+  "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-2.7B-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 70456 with parameters:
+```
+{'batch_size': 8}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 7045,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 0.0002
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 7046,
+    "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': 2560, '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 +1,82 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-2.7B",
+  "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",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      16
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 20,
+  "num_layers": 32,
+  "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-2.7B-weightedmean-nli-bitfit_weighted_mean_layer-1_results_average_precision.json

@@ -0,0 +1,7 @@
+{
+    "askubuntu": 57.48,
+    "cqadupstack": 14.04,
+    "twitterpara": 73.4,
+    "scidocs": 74.69,
+    "avg": 54.9025
+}

eval/SGPT-2.7B-weightedmean-nli-bitfit_weighted_mean_layer-1_results_detailed.json

@@ -0,0 +1,66 @@
+{
+    "askubuntu": {
+        "map_askubuntu_title": 57.48,
+        "p@1_askubuntu_title": 56.99,
+        "p@5_askubuntu_title": 43.23,
+        "mrr_askubuntu_title": 70.74
+    },
+    "cqadupstack": {
+        "map@100_cqadupstack_unix": 14.82,
+        "ndcg@10_cqadupstack_unix": 16.39,
+        "map@100_cqadupstack_gaming": 26.14,
+        "ndcg@10_cqadupstack_gaming": 28.7,
+        "map@100_cqadupstack_wordpress": 4.64,
+        "ndcg@10_cqadupstack_wordpress": 5.88,
+        "map@100_cqadupstack_stats": 15.42,
+        "ndcg@10_cqadupstack_stats": 16.15,
+        "map@100_cqadupstack_tex": 8.28,
+        "ndcg@10_cqadupstack_tex": 8.96,
+        "map@100_cqadupstack_english": 15.02,
+        "ndcg@10_cqadupstack_english": 16.54,
+        "map@100_cqadupstack_programmers": 13.27,
+        "ndcg@10_cqadupstack_programmers": 14.41,
+        "map@100_cqadupstack_mathematica": 11.74,
+        "ndcg@10_cqadupstack_mathematica": 13.47,
+        "map@100_cqadupstack_physics": 16.81,
+        "ndcg@10_cqadupstack_physics": 18.61,
+        "map@100_cqadupstack_gis": 15.47,
+        "ndcg@10_cqadupstack_gis": 16.67,
+        "map@100_cqadupstack_webmasters": 9.72,
+        "ndcg@10_cqadupstack_webmasters": 10.48,
+        "map@100_cqadupstack_android": 17.12,
+        "ndcg@10_cqadupstack_android": 19.1,
+        "map@100_cqadupstack_avg": 14.04,
+        "ndcg@10_cqadupstack_avg": 15.45
+    },
+    "twitterpara": {
+        "ap_twitter_twitterurl": 75.84,
+        "spearman_twitter_twitterurl": 70.81,
+        "ap_twitter_pit": 70.96,
+        "spearman_twitter_pit": 56.64,
+        "ap_twitter_avg": 73.4,
+        "spearman_twitter_avg": 63.73
+    },
+    "scidocs": {
+        "map_scidocs_cite_euclidean": 72.29,
+        "ndcg_scidocs_cite_euclidean": 86.43,
+        "map_scidocs_cite_cosine": 72.29,
+        "ndcg_scidocs_cite_cosine": 86.43,
+        "map_scidocs_cocite_euclidean": 75.36,
+        "ndcg_scidocs_cocite_euclidean": 88.17,
+        "map_scidocs_cocite_cosine": 75.36,
+        "ndcg_scidocs_cocite_cosine": 88.17,
+        "map_scidocs_coview_euclidean": 76.46,
+        "ndcg_scidocs_coview_euclidean": 87.8,
+        "map_scidocs_coview_cosine": 76.46,
+        "ndcg_scidocs_coview_cosine": 87.8,
+        "map_scidocs_coread_euclidean": 74.65,
+        "ndcg_scidocs_coread_euclidean": 87.0,
+        "map_scidocs_coread_cosine": 74.65,
+        "ndcg_scidocs_coread_cosine": 87.0,
+        "map_scidocs_euclidean_avg": 74.69,
+        "ndcg_scidocs_euclidean_avg": 87.35,
+        "map_scidocs_cosine_avg": 74.69,
+        "ndcg_scidocs_cosine_avg": 87.35
+    }
+}

eval/quora.json

@@ -0,0 +1 @@
+{"SGPT-2.7B-weightedmean-nli-bitfit": {"quora": {"NDCG@1": 0.7461, "NDCG@3": 0.79099, "NDCG@5": 0.80989, "NDCG@10": 0.82645, "NDCG@100": 0.84542, "NDCG@1000": 0.8478}}}

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
+0,440,0.8547642811744708,0.8604042254467369,0.8564294919751527,0.8580900991676403,0.8592109600985026,0.8606819249266364,0.7727095196030622,0.7702266970220912
+0,880,0.8605577862452674,0.8664787776815549,0.8594251818914206,0.8613580463896765,0.8625107129203857,0.8646695024116025,0.7777588243182069,0.7747923460803676
+0,1320,0.8641797068951016,0.8701385809189678,0.8600269510402324,0.8623718727121046,0.8630083477192438,0.8655171844912587,0.7819169473167653,0.7801439440796124
+0,1760,0.863861676991937,0.8699711768888497,0.8610538565702486,0.8639273844617363,0.8638166020097834,0.8668464202840234,0.7762041862089968,0.7743392283299438
+0,2200,0.8667562252351253,0.8722428457163393,0.8609922973987619,0.8640152137038429,0.8637144738269167,0.866880911411029,0.7797478785593531,0.7772643228752733
+0,2640,0.8658548494423817,0.8702345916613825,0.8583041242377912,0.8613687812725296,0.8606700693927242,0.8638960499205391,0.7781537908033099,0.7761412829543439
+0,3080,0.8643810926871549,0.8692556763950754,0.857059374227981,0.8600999939200575,0.8594169577592663,0.8625821753483399,0.7756975962910497,0.7737551514144106
+0,3520,0.8661238263202532,0.8701186430665476,0.8576723473616406,0.8614191549727733,0.8600335298933423,0.8639555339473548,0.777608544440925,0.7758958610767906
+0,3960,0.8659908588458113,0.8699200451809654,0.8570869831042444,0.860628569017929,0.8594235992474281,0.8631523750300969,0.7746604455122261,0.7731850887434243
+0,4400,0.8662536580670237,0.8702266564863804,0.8571446774934243,0.8608170966035958,0.8594735292127258,0.8633222114462352,0.7763396949906898,0.7751198872316742
+0,-1,0.8662583413659,0.8702579991508459,0.8571471752177104,0.8608379873119169,0.8594701305965878,0.8633306420570356,0.7763449731290442,0.7751015402439239

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,-1,0.8391456868332672,0.8466346397745724,0.8352041704150074,0.8363291003222771,0.8369317879915439,0.8385788509219374,0.7345451515355464,0.7176283688660806

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-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3328d67e21cfc12696ed04be3b111723b5d0e712ecc53de8cacf360745de42c5
+size 9996965077

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020dafb349b69af0f5e674afb6950199a2b705093f1a618500e9a55809240b52
+size 742637183

pytorch_model.bin.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faacf954a349388fab25a3b20e1f0a1e09d87d1eb840569b3af5e4333b3785a
+size 32846

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-2.7B", "errors": "replace", "pad_token": null, "add_bos_token": false, "tokenizer_class": "GPT2Tokenizer"}