add app.py

app.py

@@ -0,0 +1,93 @@
+Hugging Face's logo
+Hugging Face
+Search models, datasets, users...
+Models
+Datasets
+Spaces
+Docs
+Solutions
+Pricing
+
+
+
+Spaces:
+
+lewiswu1209
+/
+gpt2-chinese-couplet Copied
+like
+0
+App
+Files and versions
+Community
+gpt2-chinese-couplet
+/
+app.py
+lewiswu1209's picture
+lewiswu1209
+initial commit
+147e546
+19 days ago
+raw
+history
+blame
+contribute
+delete
+Safe
+2.07 kB
+
+import torch
+
+import gradio as gr
+import torch.nn.functional as F
+
+from transformers import BertTokenizer, GPT2LMHeadModel
+
+tokenizer = BertTokenizer.from_pretrained("uer/gpt2-chinese-couplet")
+model = GPT2LMHeadModel.from_pretrained("uer/gpt2-chinese-couplet")
+model.eval()
+
+def top_k_top_p_filtering( logits, top_k=0, top_p=0.0, filter_value=-float('Inf') ):
+    assert logits.dim() == 1
+    top_k = min( top_k, logits.size(-1) )
+    if top_k > 0:
+        indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
+        logits[indices_to_remove] = filter_value
+    if top_p > 0.0:
+        sorted_logits, sorted_indices = torch.sort(logits, descending=True)
+        cumulative_probs = torch.cumsum( F.softmax(sorted_logits, dim=-1), dim=-1 )
+        sorted_indices_to_remove = cumulative_probs > top_p
+        sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
+        sorted_indices_to_remove[..., 0] = 0
+        indices_to_remove = sorted_indices[sorted_indices_to_remove]
+        logits[indices_to_remove] = filter_value
+    return logits
+
+def generate(input_text):
+    input_ids = [tokenizer.cls_token_id]
+    input_ids.extend( tokenizer.encode(input_text + "-", add_special_tokens=False) )
+    input_ids = torch.tensor( [input_ids] )
+
+    generated = []
+    for _ in range(100):
+        output = model(input_ids)
+
+        next_token_logits = output.logits[0, -1, :]
+        next_token_logits[ tokenizer.convert_tokens_to_ids('[UNK]') ] = -float('Inf')
+        filtered_logits = top_k_top_p_filtering(next_token_logits, top_k=8, top_p=1)
+        next_token = torch.multinomial( F.softmax(filtered_logits, dim=-1), num_samples=1 )
+        if next_token == tokenizer.sep_token_id:
+            break
+        generated.append( next_token.item() )
+        input_ids = torch.cat( (input_ids, next_token.unsqueeze(0)), dim=1 )
+
+    return "".join( tokenizer.convert_ids_to_tokens(generated) )
+
+if __name__ == "__main__":
+
+    gr.Interface(
+        fn=generate,
+        inputs="text",
+        outputs="text"
+    ).launch()
+