Muennighoff commited on
Commit
41f9792
1 Parent(s): 8e851fe

Add SGPT-125M-weightedmean-msmarco-specb-bitfit

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
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 768 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
+ `torch.utils.data.dataloader.DataLoader` of length 15600 with parameters:
49
+ ```
50
+ {'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
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": 10,
64
+ "evaluation_steps": 0,
65
+ "evaluator": "NoneType",
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": 1000,
74
+ "weight_decay": 0.01
75
+ }
76
+ ```
77
+
78
+
79
+ ## Full Model Architecture
80
+ ```
81
+ SentenceTransformer(
82
+ (0): Transformer({'max_seq_length': 300, 'do_lower_case': False}) with Transformer model: GPTNeoModel
83
+ (1): Pooling({'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})
84
+ )
85
+ ```
86
+
87
+ ## Citing & Authors
88
+
89
+ <!--- Describe where people can find more information -->
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"{SOS}": 50258, "[SOS]": 50257}
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
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
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.11.3",
51
+ "use_cache": true,
52
+ "vocab_size": 50259,
53
+ "window_size": 256
54
+ }
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
+ }
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:ff8eb75758c05dbb0d40d5e4fea9ec8b707b5bb50d3e439d05273bb0b6b0c16b
3
+ size 551196689
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 300,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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.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, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff