new_code
This commit is contained in:
ahmed531998
parent
3a69bda358
commit
6a33449b25
|
|
@ -1,7 +0,0 @@
|
||||||
{
|
|
||||||
"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
|
|
||||||
}
|
|
||||||
|
|
@ -1,129 +0,0 @@
|
||||||
---
|
|
||||||
pipeline_tag: sentence-similarity
|
|
||||||
tags:
|
|
||||||
- sentence-transformers
|
|
||||||
- feature-extraction
|
|
||||||
- sentence-similarity
|
|
||||||
- transformers
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
# {MODEL_NAME}
|
|
||||||
|
|
||||||
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.
|
|
||||||
|
|
||||||
<!--- Describe your model here -->
|
|
||||||
|
|
||||||
## 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 = ["This is an example sentence", "Each sentence is converted"]
|
|
||||||
|
|
||||||
model = SentenceTransformer('{MODEL_NAME}')
|
|
||||||
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 = ['This is an example sentence', 'Each sentence is converted']
|
|
||||||
|
|
||||||
# Load model from HuggingFace Hub
|
|
||||||
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
|
|
||||||
model = AutoModel.from_pretrained('{MODEL_NAME}')
|
|
||||||
|
|
||||||
# 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)
|
|
||||||
```
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## Evaluation Results
|
|
||||||
|
|
||||||
<!--- Describe how your model was evaluated -->
|
|
||||||
|
|
||||||
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
|
||||||
|
|
||||||
|
|
||||||
## Training
|
|
||||||
The model was trained with the parameters:
|
|
||||||
|
|
||||||
**DataLoader**:
|
|
||||||
|
|
||||||
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 21515 with parameters:
|
|
||||||
```
|
|
||||||
{'batch_size': 8}
|
|
||||||
```
|
|
||||||
|
|
||||||
**Loss**:
|
|
||||||
|
|
||||||
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
|
||||||
```
|
|
||||||
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
|
||||||
```
|
|
||||||
|
|
||||||
Parameters of the fit()-Method:
|
|
||||||
```
|
|
||||||
{
|
|
||||||
"epochs": 5,
|
|
||||||
"evaluation_steps": 0,
|
|
||||||
"evaluator": "NoneType",
|
|
||||||
"max_grad_norm": 1,
|
|
||||||
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
|
||||||
"optimizer_params": {
|
|
||||||
"lr": 2e-05
|
|
||||||
},
|
|
||||||
"scheduler": "WarmupLinear",
|
|
||||||
"steps_per_epoch": null,
|
|
||||||
"warmup_steps": 10757,
|
|
||||||
"weight_decay": 0.01
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
|
|
||||||
## Full Model Architecture
|
|
||||||
```
|
|
||||||
SentenceTransformer(
|
|
||||||
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
|
|
||||||
(1): Pooling({'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})
|
|
||||||
)
|
|
||||||
```
|
|
||||||
|
|
||||||
## Citing & Authors
|
|
||||||
|
|
||||||
<!--- Describe where people can find more information -->
|
|
||||||
|
|
@ -1,24 +0,0 @@
|
||||||
{
|
|
||||||
"_name_or_path": "microsoft/mpnet-base",
|
|
||||||
"architectures": [
|
|
||||||
"MPNetModel"
|
|
||||||
],
|
|
||||||
"attention_probs_dropout_prob": 0.1,
|
|
||||||
"bos_token_id": 0,
|
|
||||||
"eos_token_id": 2,
|
|
||||||
"hidden_act": "gelu",
|
|
||||||
"hidden_dropout_prob": 0.1,
|
|
||||||
"hidden_size": 768,
|
|
||||||
"initializer_range": 0.02,
|
|
||||||
"intermediate_size": 3072,
|
|
||||||
"layer_norm_eps": 1e-05,
|
|
||||||
"max_position_embeddings": 514,
|
|
||||||
"model_type": "mpnet",
|
|
||||||
"num_attention_heads": 12,
|
|
||||||
"num_hidden_layers": 12,
|
|
||||||
"pad_token_id": 1,
|
|
||||||
"relative_attention_num_buckets": 32,
|
|
||||||
"torch_dtype": "float32",
|
|
||||||
"transformers_version": "4.20.1",
|
|
||||||
"vocab_size": 30527
|
|
||||||
}
|
|
||||||
|
|
@ -1,7 +0,0 @@
|
||||||
{
|
|
||||||
"__version__": {
|
|
||||||
"sentence_transformers": "2.2.2",
|
|
||||||
"transformers": "4.20.1",
|
|
||||||
"pytorch": "1.12.0"
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
@ -1,14 +0,0 @@
|
||||||
[
|
|
||||||
{
|
|
||||||
"idx": 0,
|
|
||||||
"name": "0",
|
|
||||||
"path": "",
|
|
||||||
"type": "sentence_transformers.models.Transformer"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"idx": 1,
|
|
||||||
"name": "1",
|
|
||||||
"path": "1_Pooling",
|
|
||||||
"type": "sentence_transformers.models.Pooling"
|
|
||||||
}
|
|
||||||
]
|
|
||||||
|
|
@ -1,4 +0,0 @@
|
||||||
{
|
|
||||||
"max_seq_length": 512,
|
|
||||||
"do_lower_case": false
|
|
||||||
}
|
|
||||||
|
|
@ -1,15 +0,0 @@
|
||||||
{
|
|
||||||
"bos_token": "<s>",
|
|
||||||
"cls_token": "<s>",
|
|
||||||
"eos_token": "</s>",
|
|
||||||
"mask_token": {
|
|
||||||
"content": "<mask>",
|
|
||||||
"lstrip": true,
|
|
||||||
"normalized": false,
|
|
||||||
"rstrip": false,
|
|
||||||
"single_word": false
|
|
||||||
},
|
|
||||||
"pad_token": "<pad>",
|
|
||||||
"sep_token": "</s>",
|
|
||||||
"unk_token": "[UNK]"
|
|
||||||
}
|
|
||||||
File diff suppressed because it is too large
Load Diff
|
|
@ -1,16 +0,0 @@
|
||||||
{
|
|
||||||
"bos_token": "<s>",
|
|
||||||
"cls_token": "<s>",
|
|
||||||
"do_lower_case": true,
|
|
||||||
"eos_token": "</s>",
|
|
||||||
"mask_token": "<mask>",
|
|
||||||
"model_max_length": 512,
|
|
||||||
"name_or_path": "microsoft/mpnet-base",
|
|
||||||
"pad_token": "<pad>",
|
|
||||||
"sep_token": "</s>",
|
|
||||||
"special_tokens_map_file": null,
|
|
||||||
"strip_accents": null,
|
|
||||||
"tokenize_chinese_chars": true,
|
|
||||||
"tokenizer_class": "MPNetTokenizer",
|
|
||||||
"unk_token": "[UNK]"
|
|
||||||
}
|
|
||||||
30527
BigRetriever/vocab.txt
30527
BigRetriever/vocab.txt
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue