Duplicate from lewiswu1209/gpt2-chinese-composition

Co-authored-by: lewiswu1209 <lewiswu1209@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.wasm 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

README.md

@@ -0,0 +1,14 @@
+---
+title: Gpt2 Chinese Composition
+emoji: 🐢
+colorFrom: yellow
+colorTo: blue
+sdk: gradio
+sdk_version: 3.0.26
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: lewiswu1209/gpt2-chinese-composition
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,70 @@
+
+import torch
+
+import gradio as gr
+import torch.nn.functional as F
+
+from transformers import GPT2LMHeadModel, CpmTokenizer
+
+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(title, context, max_len):
+    title_ids = tokenizer.encode(title, add_special_tokens=False)
+    context_ids = tokenizer.encode(context, add_special_tokens=False)
+    input_ids = title_ids + [sep_id] + context_ids
+    cur_len = len(input_ids)
+    input_len = cur_len
+    last_token_id = input_ids[-1]
+    input_ids = torch.tensor([input_ids], dtype=torch.long)
+
+    while True:
+        outputs = model( input_ids=input_ids[:, -200:] )
+        logits = outputs.logits
+        next_token_logits = logits[0, -1, :]
+        next_token_logits = next_token_logits / 1
+        next_token_logits[unk_id] = -float('Inf')
+        filtered_logits = top_k_top_p_filtering(next_token_logits, top_k=0, top_p=0.85)
+        next_token_id = torch.multinomial( F.softmax(filtered_logits, dim=-1), num_samples=1 )
+        input_ids = torch.cat( ( input_ids, next_token_id.unsqueeze(0) ), dim=1 )
+        cur_len += 1
+        word = tokenizer.convert_ids_to_tokens( next_token_id.item() )
+        if cur_len >= ( input_len + max_len ) and last_token_id == 8 and next_token_id == 3:
+            break
+        if cur_len >= ( input_len + max_len ) and word in [".", "。", "！", "!", "?", "？", ",", "，"]:
+            break
+        if next_token_id == eod_id:
+            break
+    result = tokenizer.decode( input_ids.squeeze(0) )
+    return result
+
+if __name__ == '__main__':
+    tokenizer = CpmTokenizer(vocab_file="chinese_vocab.model")
+    eod_id = tokenizer.convert_tokens_to_ids("<eod>")
+    sep_id = tokenizer.sep_token_id
+    unk_id = tokenizer.unk_token_id
+
+    model = GPT2LMHeadModel.from_pretrained("lewiswu1209/gpt2-chinese-composition")
+    model.eval()
+    gr.Interface(
+        fn=generate,
+        inputs=[
+            "text",
+            gr.Textbox(lines=7, placeholder="在这里输入一个开头。"),
+            "number"
+            ],
+        outputs=gr.Textbox(lines=15, placeholder="这里会输出一段文字。")
+    ).launch()

chinese_vocab.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c1d178d54901291c1735cd2ae0788be90df4de01fb445e8a8a998cab35ba43
+size 713229

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+sentencepiece
+jieba