初始化项目,由ModelHub XC社区提供模型
Model: Muennighoff/SGPT-125M-weightedmean-nli-bitfit Source: Original Platform
This commit is contained in:
27
.gitattributes
vendored
Normal file
27
.gitattributes
vendored
Normal file
@@ -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
|
||||
9
1_Pooling/config.json
Normal file
9
1_Pooling/config.json
Normal file
@@ -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": true,
|
||||
"pooling_mode_lasttoken": false
|
||||
}
|
||||
54
config.json
Normal file
54
config.json
Normal file
@@ -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": "4.20.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50257,
|
||||
"window_size": 256
|
||||
}
|
||||
7
config_sentence_transformers.json
Normal file
7
config_sentence_transformers.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"__version__": {
|
||||
"sentence_transformers": "2.1.0",
|
||||
"transformers": "4.20.0.dev0",
|
||||
"pytorch": "1.10.2"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"askubuntu": 55.66,
|
||||
"cqadupstack": 11.13,
|
||||
"twitterpara": 69.63,
|
||||
"scidocs": 68.01,
|
||||
"avg": 51.1075
|
||||
}
|
||||
@@ -0,0 +1,66 @@
|
||||
{
|
||||
"askubuntu": {
|
||||
"map_askubuntu_title": 55.66,
|
||||
"p@1_askubuntu_title": 51.61,
|
||||
"p@5_askubuntu_title": 41.4,
|
||||
"mrr_askubuntu_title": 66.68
|
||||
},
|
||||
"cqadupstack": {
|
||||
"map@100_cqadupstack_unix": 10.86,
|
||||
"ndcg@10_cqadupstack_unix": 11.65,
|
||||
"map@100_cqadupstack_gaming": 20.48,
|
||||
"ndcg@10_cqadupstack_gaming": 22.59,
|
||||
"map@100_cqadupstack_wordpress": 4.11,
|
||||
"ndcg@10_cqadupstack_wordpress": 4.52,
|
||||
"map@100_cqadupstack_stats": 13.42,
|
||||
"ndcg@10_cqadupstack_stats": 13.69,
|
||||
"map@100_cqadupstack_tex": 7.05,
|
||||
"ndcg@10_cqadupstack_tex": 7.4,
|
||||
"map@100_cqadupstack_english": 8.84,
|
||||
"ndcg@10_cqadupstack_english": 10.03,
|
||||
"map@100_cqadupstack_programmers": 10.39,
|
||||
"ndcg@10_cqadupstack_programmers": 10.95,
|
||||
"map@100_cqadupstack_mathematica": 9.81,
|
||||
"ndcg@10_cqadupstack_mathematica": 10.84,
|
||||
"map@100_cqadupstack_physics": 13.33,
|
||||
"ndcg@10_cqadupstack_physics": 13.56,
|
||||
"map@100_cqadupstack_gis": 13.79,
|
||||
"ndcg@10_cqadupstack_gis": 14.32,
|
||||
"map@100_cqadupstack_webmasters": 8.58,
|
||||
"ndcg@10_cqadupstack_webmasters": 9.35,
|
||||
"map@100_cqadupstack_android": 12.86,
|
||||
"ndcg@10_cqadupstack_android": 14.72,
|
||||
"map@100_cqadupstack_avg": 11.13,
|
||||
"ndcg@10_cqadupstack_avg": 11.97
|
||||
},
|
||||
"twitterpara": {
|
||||
"ap_twitter_twitterurl": 72.79,
|
||||
"spearman_twitter_twitterurl": 67.64,
|
||||
"ap_twitter_pit": 66.47,
|
||||
"spearman_twitter_pit": 47.88,
|
||||
"ap_twitter_avg": 69.63,
|
||||
"spearman_twitter_avg": 57.76
|
||||
},
|
||||
"scidocs": {
|
||||
"map_scidocs_cite_euclidean": 65.13,
|
||||
"ndcg_scidocs_cite_euclidean": 82.16,
|
||||
"map_scidocs_cite_cosine": 65.13,
|
||||
"ndcg_scidocs_cite_cosine": 82.16,
|
||||
"map_scidocs_cocite_euclidean": 67.76,
|
||||
"ndcg_scidocs_cocite_euclidean": 83.77,
|
||||
"map_scidocs_cocite_cosine": 67.76,
|
||||
"ndcg_scidocs_cocite_cosine": 83.77,
|
||||
"map_scidocs_coview_euclidean": 70.51,
|
||||
"ndcg_scidocs_coview_euclidean": 84.5,
|
||||
"map_scidocs_coview_cosine": 70.51,
|
||||
"ndcg_scidocs_coview_cosine": 84.5,
|
||||
"map_scidocs_coread_euclidean": 68.62,
|
||||
"ndcg_scidocs_coread_euclidean": 83.66,
|
||||
"map_scidocs_coread_cosine": 68.62,
|
||||
"ndcg_scidocs_coread_cosine": 83.66,
|
||||
"map_scidocs_euclidean_avg": 68.01,
|
||||
"ndcg_scidocs_euclidean_avg": 83.52,
|
||||
"map_scidocs_cosine_avg": 68.01,
|
||||
"ndcg_scidocs_cosine_avg": 83.52
|
||||
}
|
||||
}
|
||||
1
eval/quora.json
Normal file
1
eval/quora.json
Normal file
@@ -0,0 +1 @@
|
||||
{"SGPT-125M-weightedmean-nli-bitfit": {"quora": {"NDCG@1": 0.7097, "NDCG@3": 0.75264, "NDCG@5": 0.77096, "NDCG@10": 0.78967, "NDCG@100": 0.81262, "NDCG@1000": 0.81682}}}
|
||||
12
eval/similarity_evaluation_sts-dev_results.csv
Normal file
12
eval/similarity_evaluation_sts-dev_results.csv
Normal file
@@ -0,0 +1,12 @@
|
||||
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
|
||||
0,440,0.815931462953464,0.8200562029402142,0.8157369182150072,0.819603973090759,0.8184615924110381,0.823007690742192,0.7061069454916115,0.7112807915742094
|
||||
0,880,0.8214075065169842,0.8255189362474712,0.8192073152764299,0.8236822552646557,0.8215825733824851,0.8264104866848039,0.7174042848871002,0.7192644874753024
|
||||
0,1320,0.8281480125216174,0.8335677824006662,0.8218868633996832,0.8269437148107974,0.8243453247825011,0.8296731348438655,0.7260606000892722,0.7296375462352843
|
||||
0,1760,0.8288444853328012,0.8336538155269189,0.8228072115324837,0.8279187688644755,0.8240960132575046,0.8296670547684952,0.7297739366603081,0.7327912957426814
|
||||
0,2200,0.8322285781163465,0.8363460131143705,0.8238595252888139,0.8285953867691392,0.8251293855185525,0.8303417242732376,0.7321514272161418,0.7343360548158535
|
||||
0,2640,0.8316032894200165,0.8360248029282871,0.8229876867952128,0.8274986778272352,0.8247887992125305,0.829730972962072,0.735861995734252,0.7394614515913788
|
||||
0,3080,0.8307132415525218,0.8357857422650881,0.821973667735502,0.8268832848991191,0.8232670133914585,0.8287163832939213,0.7351494187227637,0.7373781263102374
|
||||
0,3520,0.8321450278222416,0.837515610006931,0.8227498428419581,0.8276296120812954,0.824194673798708,0.8294918695942172,0.7350862168960725,0.7385545256985955
|
||||
0,3960,0.8324321317037187,0.8372050831022416,0.8235292210527604,0.8280796389286461,0.8251002162736456,0.8299533503397363,0.7325730558165168,0.7364960367335265
|
||||
0,4400,0.832333153640081,0.8370257982810063,0.8227920398931506,0.8274093432460116,0.8243812864875318,0.829381817916846,0.7344786676900655,0.7383103767201893
|
||||
0,-1,0.8323134689045238,0.8369988089385374,0.8227832000988474,0.8274006510691946,0.8243732697450359,0.8293464655792817,0.7344279740920635,0.7383348227000012
|
||||
|
2
eval/similarity_evaluation_sts-test_results.csv
Normal file
2
eval/similarity_evaluation_sts-test_results.csv
Normal file
@@ -0,0 +1,2 @@
|
||||
epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
|
||||
-1,-1,0.8000926257222208,0.7953985460102709,0.7952025212260427,0.78929372286714,0.7947603682819968,0.7906380658888169,0.6312256336304743,0.612896395113368
|
||||
|
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
14
modules.json
Normal file
14
modules.json
Normal file
@@ -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"
|
||||
}
|
||||
]
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6f48a127abdc03ef0217e1305a1ef41759c398b23a9bc8d51e9e5dc9bca3dae5
|
||||
size 551182929
|
||||
4
sentence_bert_config.json
Normal file
4
sentence_bert_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"max_seq_length": 75,
|
||||
"do_lower_case": false
|
||||
}
|
||||
1
special_tokens_map.json
Normal file
1
special_tokens_map.json
Normal file
@@ -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|>"}
|
||||
100316
tokenizer.json
Normal file
100316
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
1
tokenizer_config.json
Normal file
1
tokenizer_config.json
Normal file
@@ -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", "pad_token": null, "add_bos_token": false, "tokenizer_class": "GPT2Tokenizer"}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user