初始化项目，由ModelHub XC社区提供模型
Model: efederici/sentence-it5-base Source: Original Platform
This commit is contained in:
ModelHub XC
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
|
||||
7
1_Pooling/config.json
Normal file
7
1_Pooling/config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"word_embedding_dimension": 768,
|
||||
"pooling_mode_cls_token": false,
|
||||
"pooling_mode_mean_tokens": true,
|
||||
"pooling_mode_max_tokens": false,
|
||||
"pooling_mode_mean_sqrt_len_tokens": false
|
||||
}
|
||||
79
README.md
Normal file
79
README.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
pipeline_tag: sentence-similarity
|
||||
language:
|
||||
- it
|
||||
tags:
|
||||
- sentence-transformers
|
||||
- feature-extraction
|
||||
- sentence-similarity
|
||||
- transformers
|
||||
---
|
||||
|
||||
# sentence-IT5-base
|
||||
|
||||
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search. It is a T5 ([IT5](https://huggingface.co/gsarti/it5-base)) base model. It is trained on a dataset made from question/context pairs ([squad-it](https://github.com/crux82/squad-it)), tags/news-article pairs, headline/text pairs ([change-it](https://huggingface.co/datasets/gsarti/change_it)) and on [stsb](https://huggingface.co/datasets/stsb_multi_mt/viewer/it/train).
|
||||
|
||||
## Usage (Sentence-Transformers)
|
||||
|
||||
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
||||
|
||||
```
|
||||
pip install -U sentence-transformers
|
||||
```
|
||||
|
||||
Then you can use the model like this:
|
||||
|
||||
```python
|
||||
from sentence_transformers import SentenceTransformer
|
||||
sentences = ["Questo è un esempio di frase", "Questo è un ulteriore esempio"]
|
||||
|
||||
model = SentenceTransformer('efederici/sentence-IT5-base')
|
||||
embeddings = model.encode(sentences)
|
||||
print(embeddings)
|
||||
```
|
||||
|
||||
|
||||
|
||||
## Usage (HuggingFace Transformers)
|
||||
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModel
|
||||
import torch
|
||||
|
||||
|
||||
#Mean Pooling - Take attention mask into account for correct averaging
|
||||
def mean_pooling(model_output, attention_mask):
|
||||
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
||||
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
||||
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
||||
|
||||
|
||||
# Sentences we want sentence embeddings for
|
||||
sentences = ["Questo è un esempio di frase", "Questo è un ulteriore esempio"]
|
||||
|
||||
# Load model from HuggingFace Hub
|
||||
tokenizer = AutoTokenizer.from_pretrained('efederici/sentence-IT5-base')
|
||||
model = AutoModel.from_pretrained('efederici/sentence-IT5-base')
|
||||
|
||||
# Tokenize sentences
|
||||
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
||||
|
||||
# Compute token embeddings
|
||||
with torch.no_grad():
|
||||
model_output = model(**encoded_input)
|
||||
|
||||
# Perform pooling. In this case, mean pooling.
|
||||
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
||||
|
||||
print("Sentence embeddings:")
|
||||
print(sentence_embeddings)
|
||||
```
|
||||
|
||||
## Full Model Architecture
|
||||
```
|
||||
SentenceTransformer(
|
||||
(0): Transformer({'max_seq_length': None, 'do_lower_case': False}) with Transformer model: T5EncoderModel
|
||||
(1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
||||
)
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/content/model/model_sent/",
|
||||
"architectures": [
|
||||
"T5EncoderModel"
|
||||
],
|
||||
"d_ff": 2048,
|
||||
"d_kv": 64,
|
||||
"d_model": 768,
|
||||
"decoder_start_token_id": 0,
|
||||
"dropout_rate": 0.1,
|
||||
"eos_token_id": 1,
|
||||
"feed_forward_proj": "gated-gelu",
|
||||
"gradient_checkpointing": false,
|
||||
"initializer_factor": 1.0,
|
||||
"is_encoder_decoder": true,
|
||||
"layer_norm_epsilon": 1e-06,
|
||||
"model_type": "t5",
|
||||
"num_decoder_layers": 12,
|
||||
"num_heads": 12,
|
||||
"num_layers": 12,
|
||||
"output_past": true,
|
||||
"pad_token_id": 0,
|
||||
"relative_attention_num_buckets": 32,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.17.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32103
|
||||
}
|
||||
7
config_sentence_transformers.json
Normal file
7
config_sentence_transformers.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"__version__": {
|
||||
"sentence_transformers": "2.2.0",
|
||||
"transformers": "4.17.0",
|
||||
"pytorch": "1.10.0+cu111"
|
||||
}
|
||||
}
|
||||
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 sha256:38568de552d941767be7d5f46f1fa038d0624d2b14c811dc962168511946461a
|
||||
size 438488035
|
||||
4
sentence_bert_config.json
Normal file
4
sentence_bert_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"max_seq_length": null,
|
||||
"do_lower_case": false
|
||||
}
|
||||
1
special_tokens_map.json
Normal file
1
special_tokens_map.json
Normal file
@@ -0,0 +1 @@
|
||||
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
||||
129045
tokenizer.json
Normal file
129045
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 @@
|
||||
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "/content/model/model_sent/", "tokenizer_class": "T5Tokenizer"}
|
||||
Reference in New Issue
Block a user