Upload folder using huggingface_hub
Browse files- 2_Dense/pytorch_model.bin +2 -2
- README.md +6 -6
- config.json +2 -2
- model.safetensors +1 -1
- tokenizer_config.json +0 -7
2_Dense/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3a940c1d18f7dc625d5117543c14678721061a2f85350ac6973917ee134f5cc
|
3 |
+
size 2363964
|
README.md
CHANGED
@@ -8,7 +8,7 @@ tags:
|
|
8 |
|
9 |
---
|
10 |
|
11 |
-
#
|
12 |
|
13 |
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.
|
14 |
|
@@ -28,7 +28,7 @@ Then you can use the model like this:
|
|
28 |
from sentence_transformers import SentenceTransformer
|
29 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
|
31 |
-
model = SentenceTransformer('
|
32 |
embeddings = model.encode(sentences)
|
33 |
print(embeddings)
|
34 |
```
|
@@ -47,7 +47,7 @@ The model was trained with the parameters:
|
|
47 |
|
48 |
**DataLoader**:
|
49 |
|
50 |
-
`torch.utils.data.dataloader.DataLoader` of length
|
51 |
```
|
52 |
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
53 |
```
|
@@ -62,17 +62,17 @@ The model was trained with the parameters:
|
|
62 |
Parameters of the fit()-Method:
|
63 |
```
|
64 |
{
|
65 |
-
"epochs":
|
66 |
"evaluation_steps": 100,
|
67 |
"evaluator": "__main__.ChainScoreEvaluator",
|
68 |
"max_grad_norm": 1,
|
69 |
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
70 |
"optimizer_params": {
|
71 |
-
"lr":
|
72 |
},
|
73 |
"scheduler": "warmupcosine",
|
74 |
"steps_per_epoch": null,
|
75 |
-
"warmup_steps":
|
76 |
"weight_decay": 0.01
|
77 |
}
|
78 |
```
|
|
|
8 |
|
9 |
---
|
10 |
|
11 |
+
# {MODEL_NAME}
|
12 |
|
13 |
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.
|
14 |
|
|
|
28 |
from sentence_transformers import SentenceTransformer
|
29 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
|
31 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
32 |
embeddings = model.encode(sentences)
|
33 |
print(embeddings)
|
34 |
```
|
|
|
47 |
|
48 |
**DataLoader**:
|
49 |
|
50 |
+
`torch.utils.data.dataloader.DataLoader` of length 9636 with parameters:
|
51 |
```
|
52 |
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
53 |
```
|
|
|
62 |
Parameters of the fit()-Method:
|
63 |
```
|
64 |
{
|
65 |
+
"epochs": 2,
|
66 |
"evaluation_steps": 100,
|
67 |
"evaluator": "__main__.ChainScoreEvaluator",
|
68 |
"max_grad_norm": 1,
|
69 |
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
70 |
"optimizer_params": {
|
71 |
+
"lr": 5e-06
|
72 |
},
|
73 |
"scheduler": "warmupcosine",
|
74 |
"steps_per_epoch": null,
|
75 |
+
"warmup_steps": 1000,
|
76 |
"weight_decay": 0.01
|
77 |
}
|
78 |
```
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
@@ -25,7 +25,7 @@
|
|
25 |
"pooler_type": "first_token_transform",
|
26 |
"position_embedding_type": "absolute",
|
27 |
"torch_dtype": "float32",
|
28 |
-
"transformers_version": "4.
|
29 |
"type_vocab_size": 2,
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 501153
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "sentence-transformers/LaBSE",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
25 |
"pooler_type": "first_token_transform",
|
26 |
"position_embedding_type": "absolute",
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.39.0",
|
29 |
"type_vocab_size": 2,
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 501153
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1883730160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad6213cd22a7905cb0bbe03e5f88adb8c0009d1ed34f1cada839a13d43186544
|
3 |
size 1883730160
|
tokenizer_config.json
CHANGED
@@ -47,19 +47,12 @@
|
|
47 |
"do_lower_case": false,
|
48 |
"full_tokenizer_file": null,
|
49 |
"mask_token": "[MASK]",
|
50 |
-
"max_length": 256,
|
51 |
"model_max_length": 512,
|
52 |
"never_split": null,
|
53 |
-
"pad_to_multiple_of": null,
|
54 |
"pad_token": "[PAD]",
|
55 |
-
"pad_token_type_id": 0,
|
56 |
-
"padding_side": "right",
|
57 |
"sep_token": "[SEP]",
|
58 |
-
"stride": 0,
|
59 |
"strip_accents": null,
|
60 |
"tokenize_chinese_chars": true,
|
61 |
"tokenizer_class": "BertTokenizer",
|
62 |
-
"truncation_side": "right",
|
63 |
-
"truncation_strategy": "longest_first",
|
64 |
"unk_token": "[UNK]"
|
65 |
}
|
|
|
47 |
"do_lower_case": false,
|
48 |
"full_tokenizer_file": null,
|
49 |
"mask_token": "[MASK]",
|
|
|
50 |
"model_max_length": 512,
|
51 |
"never_split": null,
|
|
|
52 |
"pad_token": "[PAD]",
|
|
|
|
|
53 |
"sep_token": "[SEP]",
|
|
|
54 |
"strip_accents": null,
|
55 |
"tokenize_chinese_chars": true,
|
56 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
57 |
"unk_token": "[UNK]"
|
58 |
}
|