Muennighoff commited on
Commit
b9af6e4
1 Parent(s): 8db6dce

Add SGPT-2.7B-weightedmean-nli-bitfit

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 2560,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": true,
8
+ "pooling_mode_lasttoken": false
9
+ }
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ ---
8
+
9
+ # {MODEL_NAME}
10
+
11
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 2560 dimensional dense vector space and can be used for tasks like clustering or semantic search.
12
+
13
+ <!--- Describe your model here -->
14
+
15
+ ## Usage (Sentence-Transformers)
16
+
17
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
18
+
19
+ ```
20
+ pip install -U sentence-transformers
21
+ ```
22
+
23
+ Then you can use the model like this:
24
+
25
+ ```python
26
+ from sentence_transformers import SentenceTransformer
27
+ sentences = ["This is an example sentence", "Each sentence is converted"]
28
+
29
+ model = SentenceTransformer('{MODEL_NAME}')
30
+ embeddings = model.encode(sentences)
31
+ print(embeddings)
32
+ ```
33
+
34
+
35
+
36
+ ## Evaluation Results
37
+
38
+ <!--- Describe how your model was evaluated -->
39
+
40
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
41
+
42
+
43
+ ## Training
44
+ The model was trained with the parameters:
45
+
46
+ **DataLoader**:
47
+
48
+ `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 70456 with parameters:
49
+ ```
50
+ {'batch_size': 8}
51
+ ```
52
+
53
+ **Loss**:
54
+
55
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
56
+ ```
57
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
58
+ ```
59
+
60
+ Parameters of the fit()-Method:
61
+ ```
62
+ {
63
+ "epochs": 1,
64
+ "evaluation_steps": 7045,
65
+ "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
66
+ "max_grad_norm": 1,
67
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
68
+ "optimizer_params": {
69
+ "lr": 0.0002
70
+ },
71
+ "scheduler": "WarmupLinear",
72
+ "steps_per_epoch": null,
73
+ "warmup_steps": 7046,
74
+ "weight_decay": 0.01
75
+ }
76
+ ```
77
+
78
+
79
+ ## Full Model Architecture
80
+ ```
81
+ SentenceTransformer(
82
+ (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTNeoModel
83
+ (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})
84
+ )
85
+ ```
86
+
87
+ ## Citing & Authors
88
+
89
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-2.7B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoModel"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local",
33
+ "global",
34
+ "local",
35
+ "global",
36
+ "local",
37
+ "global",
38
+ "local",
39
+ "global",
40
+ "local"
41
+ ],
42
+ "attention_types": [
43
+ [
44
+ [
45
+ "global",
46
+ "local"
47
+ ],
48
+ 16
49
+ ]
50
+ ],
51
+ "bos_token_id": 50256,
52
+ "embed_dropout": 0,
53
+ "eos_token_id": 50256,
54
+ "gradient_checkpointing": false,
55
+ "hidden_size": 2560,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": null,
58
+ "layer_norm_epsilon": 1e-05,
59
+ "max_position_embeddings": 2048,
60
+ "model_type": "gpt_neo",
61
+ "num_heads": 20,
62
+ "num_layers": 32,
63
+ "resid_dropout": 0,
64
+ "summary_activation": null,
65
+ "summary_first_dropout": 0.1,
66
+ "summary_proj_to_labels": true,
67
+ "summary_type": "cls_index",
68
+ "summary_use_proj": true,
69
+ "task_specific_params": {
70
+ "text-generation": {
71
+ "do_sample": true,
72
+ "max_length": 50,
73
+ "temperature": 0.9
74
+ }
75
+ },
76
+ "tokenizer_class": "GPT2Tokenizer",
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.11.3",
79
+ "use_cache": true,
80
+ "vocab_size": 50257,
81
+ "window_size": 256
82
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.1.0",
4
+ "transformers": "4.11.3",
5
+ "pytorch": "1.10.1"
6
+ }
7
+ }
eval/similarity_evaluation_sts-dev_results.csv ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,7045,0.854762523109346,0.8625722411777832,0.8559952110984044,0.8599071798553728,0.8562325179051519,0.8607011270217957,0.7604255385773144,0.7606474726533847
3
+ 0,14090,0.862071545726209,0.8686263495658821,0.8587162825998957,0.8617412291621442,0.8592342866823668,0.8627125269846087,0.782391853949178,0.7829935432149258
4
+ 0,21135,0.861147560133928,0.8673147899430655,0.8565176946586014,0.859934895176966,0.8562610749976107,0.8599692261614817,0.767074455302903,0.7695279716565803
5
+ 0,28180,0.8633257964426606,0.8706412335168616,0.8552663992944554,0.8599920464619075,0.8540030273419198,0.8592715940080606,0.7791548165962676,0.7857437212669921
6
+ 0,35225,0.8571401068053901,0.8634311296708672,0.8509601042154958,0.8549359573084144,0.8507577553572114,0.8553929614415839,0.7642286538174881,0.770790070391215
7
+ 0,42270,0.8598605654357643,0.8650105143335562,0.8511585774583015,0.8554589632664334,0.8505706583139645,0.8553814756685433,0.7617624805084298,0.7702625967180601
8
+ 0,49315,0.8573338952704139,0.8609427481847676,0.842483574189439,0.8467522455218017,0.8416057486283591,0.8466172561049204,0.7626709741843098,0.772898390349653
9
+ 0,56360,0.8621834500026332,0.8670699694896324,0.8505378356088411,0.8545156885949555,0.8496468004499398,0.854239264916894,0.7677057311830797,0.7762473321595961
10
+ 0,63405,0.8591097675730657,0.8630995653851116,0.8446734640853417,0.8496054770256773,0.8437993624528112,0.8492440088050155,0.7627356339474485,0.7727980219530748
11
+ 0,70450,0.8598307992062442,0.864221237988858,0.84629527410727,0.8513689337571044,0.845389605407747,0.8508766807487939,0.7613761802820678,0.7708455277248111
12
+ 0,-1,0.8598065664641443,0.8642014942030082,0.8462916558850146,0.8513545689785207,0.8453849685801835,0.8508523604473343,0.7613656467412337,0.7707829013471281
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d3fa68460291ddf0b431b9cf0beb67ea22dac2a356a732447e7f74388ce61b
3
+ size 10739623849
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 75,
3
+ "do_lower_case": false
4
+ }
similarity_evaluation_sts-test_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ -1,-1,0.8421195813886659,0.8544705934133663,0.8331975612681435,0.8365254010816424,0.8308796371031103,0.8350842363910842,0.7416086337173262,0.730738158975577
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff