File size: 2,336 Bytes
b75af72 547ac8f |
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 |
import gradio as gr
import torch
from transformers import BertForMaskedLM, BertTokenizer
import asyncio
# Modell und Tokenizer laden mit force_download=True
model_name = "bert-base-uncased"
model = BertForMaskedLM.from_pretrained(model_name, force_download=True)
tokenizer = BertTokenizer.from_pretrained(model_name, force_download=True)
# Inferenz-Funktion definieren
def inference(input_text):
if "[MASK]" not in input_text:
return "Error: The input text must contain the [MASK] token."
# Tokenisierung
inputs = tokenizer(input_text, return_tensors="pt")
mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
# Vorhersage
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits
# Wahrscheinlichsten Token für [MASK] finden
mask_token_logits = logits[0, mask_token_index, :]
top_token = torch.topk(mask_token_logits, 1, dim=1).indices[0].tolist()
# Vorhersage in den Text einfügen
predicted_token = tokenizer.decode(top_token)
result_text = input_text.replace("[MASK]", predicted_token, 1)
return result_text
# Gradio Interface definieren
iface = gr.Interface(
fn=inference,
inputs="text",
outputs="text",
examples=[
["The capital of France is [MASK]."],
["The quick brown fox jumps over the [MASK] dog."]
]
)
# Interface starten
if __name__ == "__main__":
# Asynchronen Ereignisloop manuell erstellen und zuweisen
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
iface.launch(server_port=7862)
from transformers import pipeline
unmasker = pipeline('fill-mask', model='bert-base-uncased')
unmasker("Hello I'm a [MASK] model.")
from transformers import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained("bert-base-uncased")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
from transformers import BertTokenizer, TFBertModel
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = TFBertModel.from_pretrained("bert-base-uncased")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input) |