Spaces:
Runtime error
Runtime error
File size: 6,139 Bytes
16188ba |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 |
from typing import List
from sentence_transformers import SentenceTransformer
from kmeans_pytorch import kmeans
import torch
from sklearn.cluster import KMeans
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM,Text2TextGenerationPipeline
from inference_hf import InferenceHF
from .dimension_reduction import PCA
from unsupervised_learning.clustering import GaussianMixture
from models import KeyBartAdapter
class Template:
def __init__(self):
self.PLM = {
'sentence-transformer-mini': '''sentence-transformers/all-MiniLM-L6-v2''',
'sentence-t5-xxl': '''sentence-transformers/sentence-t5-xxl''',
'all-mpnet-base-v2':'''sentence-transformers/all-mpnet-base-v2'''
}
self.dimension_reduction = {
'pca': PCA,
'vae': None,
'cnn': None
}
self.clustering = {
'kmeans-cosine': kmeans,
'kmeans-euclidean': KMeans,
'gmm': GaussianMixture
}
self.keywords_extraction = {
'keyphrase-transformer': '''snrspeaks/KeyPhraseTransformer''',
'KeyBartAdapter': '''Adapting/KeyBartAdapter''',
'KeyBart': '''bloomberg/KeyBART'''
}
template = Template()
def __create_model__(model_ckpt):
'''
:param model_ckpt: keys in Template class
:return: model/function: callable
'''
if model_ckpt == '''sentence-transformer-mini''':
return SentenceTransformer(template.PLM[model_ckpt])
elif model_ckpt == '''sentence-t5-xxl''':
return SentenceTransformer(template.PLM[model_ckpt])
elif model_ckpt == '''all-mpnet-base-v2''':
return SentenceTransformer(template.PLM[model_ckpt])
elif model_ckpt == 'none':
return None
elif model_ckpt == 'kmeans-cosine':
def ret(x,k):
tmp = template.clustering[model_ckpt](
X=torch.from_numpy(x), num_clusters=k, distance='cosine',
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
)
return tmp[0].cpu().detach().numpy(), tmp[1].cpu().detach().numpy()
return ret
elif model_ckpt == 'pca':
pca = template.dimension_reduction[model_ckpt](0.95)
return pca
elif model_ckpt =='kmeans-euclidean':
def ret(x,k):
tmp = KMeans(n_clusters=k,random_state=50).fit(x)
return tmp.labels_, tmp.cluster_centers_
return ret
elif model_ckpt == 'gmm':
def ret(x,k):
model = GaussianMixture(k,50)
model.fit(x)
return model.getLabels(), model.getClusterCenters()
return ret
elif model_ckpt == 'keyphrase-transformer':
model_ckpt = template.keywords_extraction[model_ckpt]
def ret(texts: List[str]):
# first try inference API
response = InferenceHF.inference(
inputs=texts,
model_name=model_ckpt
)
# inference failed:
if not isinstance(response, list):
tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
model = AutoModelForSeq2SeqLM.from_pretrained(model_ckpt)
pipe = Text2TextGenerationPipeline(model=model, tokenizer=tokenizer)
tmp = pipe(texts)
results = [
set(
map(str.strip,
x['generated_text'].split('|') # [str...]
)
)
for x in tmp] # [{str...}...]
return results
# inference sucsess
else:
results = [
set(
map(str.strip,
x['generated_text'].split('|') # [str...]
)
)
for x in response] # [{str...}...]
return results
return ret
elif model_ckpt == 'KeyBart':
model_ckpt = template.keywords_extraction[model_ckpt]
def ret(texts: List[str]):
# first try inference API
response = InferenceHF.inference(
inputs=texts,
model_name=model_ckpt
)
# inference failed:
if not isinstance(response,list):
tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
model = AutoModelForSeq2SeqLM.from_pretrained(model_ckpt)
pipe = Text2TextGenerationPipeline(model=model, tokenizer=tokenizer)
tmp = pipe(texts)
results = [
set(
map(str.strip,
x['generated_text'].split(';') # [str...]
)
)
for x in tmp] # [{str...}...]
return results
# inference sucsess
else:
results = [
set(
map(str.strip,
x['generated_text'].split(';') # [str...]
)
)
for x in response] # [{str...}...]
return results
return ret
elif model_ckpt == 'KeyBartAdapter':
def ret(texts: List[str]):
model = KeyBartAdapter.from_pretrained('Adapting/KeyBartAdapter',revision='3aee5ecf1703b9955ab0cd1b23208cc54eb17fce', adapter_hid_dim=32)
tokenizer = AutoTokenizer.from_pretrained("bloomberg/KeyBART")
pipe = Text2TextGenerationPipeline(model=model, tokenizer=tokenizer)
tmp = pipe(texts)
results = [
set(
map(str.strip,
x['generated_text'].split(';') # [str...]
)
)
for x in tmp] # [{str...}...]
return results
return ret
else:
raise RuntimeError(f'The model {model_ckpt} is not supported. Please open an issue on the GitHub about the model.')
|