Upload with huggingface_hub

app.py

@@ -0,0 +1,79 @@
+#from summary_reverse_pred_native import *
+#### daspartho/prompt-extend
+
+import gradio as gr
+import os
+from predict import *
+
+#device = "cuda:0"
+device = "cpu"
+assert device.startswith("cpu") or device.startswith("cuda")
+
+from transformers import (
+    T5ForConditionalGeneration,
+    MT5ForConditionalGeneration,
+    ByT5Tokenizer,
+    PreTrainedTokenizer,
+    T5TokenizerFast as T5Tokenizer,
+    MT5TokenizerFast as MT5Tokenizer,
+    AutoModelForSeq2SeqLM,
+    AutoTokenizer,
+    BertTokenizer,
+    GPT2LMHeadModel,
+)
+
+#### "svjack/prompt-extend-chinese-gpt"
+#model_path = "/home/featurize/zh_p_extend_outputs/simplet5-epoch-3-train-loss-1.2628-val-loss-1.6293"
+model_path = "svjack/prompt-extend-chinese-gpt"
+tokenizer1 = BertTokenizer.from_pretrained(model_path)
+model1 = GPT2LMHeadModel.from_pretrained(model_path)
+
+if device.startswith("cuda"):
+    zh_pe_model = Obj(model1, tokenizer1, device = "cuda:0")
+else:
+    zh_pe_model = Obj(model1, tokenizer1, device = "cpu")
+
+def one_ele_trans(x):
+    x = x.strip()
+    x = x[1:] if x.startswith("'") else x
+    x = x[:-1] if x.endswith("'") else x
+    x = x[1:] if x.startswith('"') else x
+    x = x[:-1] if x.endswith('"') else x
+    return x
+
+def stdf_prompt_expander(x, do_sample):
+    assert type(x) == type("")
+    return zh_pe_model.predict(
+    one_ele_trans(x.strip()).strip(),
+    max_length = 128,
+    do_sample = do_sample
+    )[0].replace(" ", "").strip()
+
+#text0 = "飓风格特是1993年9月在墨西哥和整个中美洲引发严重洪灾的大规模热带气旋，源于9月14日西南加勒比海上空一股东风波。次日从尼加拉瓜登岸，经过洪都拉斯后于9月17日在洪都拉斯湾再次达到热带风暴标准，但次日进入伯利兹上空后就减弱成热带低气压。穿过尤卡坦半岛后，在9月20日强化成二级飓风，从韦拉克鲁斯州的图斯潘附近登陆墨西哥。9月21日从纳亚里特州进入太平洋时已降级成热带低气压，最终于5天后在开放水域上空消散。"
+#text1 = "珊瑚坝是长江中的一处河漫滩，位于长江重庆市渝中区区段主航道左侧[1]，靠近渝中半岛，原分属重庆市市中区菜园坝街道和石板坡街道[2]，现属渝中区菜园坝街道石板坡社区[3]，是长江上游缓冲地段自然冲积沙洲，略呈纺锤形[4]或椭圆形，长约1800米，宽约600米，坝上遍布鹅卵石和水草。每年夏季洪水时均被淹没，其余时间常露水面，枯水期则与长江左岸相连[5]。"
+prompt = "一只凶猛的老虎，咬死了一只豺狼。"
+
+example_sample = [
+    [prompt, False],
+    #[text1, False],
+]
+
+def demo_func(prefix, do_sample):
+    #l = simple_pred(prefix, do_sample = do_sample)
+    x = stdf_prompt_expander(prefix, do_sample = do_sample)
+    return {
+        "Prompt extend": x
+    }
+
+demo = gr.Interface(
+        fn=demo_func,
+        inputs=[gr.Text(label = "Prompt"),
+                gr.Checkbox(label="do sample"),
+        ],
+        outputs="json",
+        title=f"Stable Diffusion Chinese Prompt Extend 🐰 demonstration",
+        examples=example_sample if example_sample else None,
+        cache_examples = False
+    )
+
+demo.launch(server_name=None, server_port=None)

predict.py

@@ -0,0 +1,47 @@
+class Obj:
+    def __init__(self, model, tokenizer, device = "cpu"):
+        self.model = model
+        self.tokenizer = tokenizer
+        self.device = device
+        self.model = self.model.to(self.device)
+
+    def predict(
+        self,
+        source_text: str,
+        max_length: int = 512,
+        num_return_sequences: int = 1,
+        num_beams: int = 2,
+        top_k: int = 50,
+        top_p: float = 0.95,
+        do_sample: bool = True,
+        repetition_penalty: float = 2.5,
+        length_penalty: float = 1.0,
+        early_stopping: bool = True,
+        skip_special_tokens: bool = True,
+        clean_up_tokenization_spaces: bool = True,
+    ):
+        input_ids = self.tokenizer.encode(
+            source_text, return_tensors="pt", add_special_tokens=True
+        )
+        input_ids = input_ids.to(self.device)
+        generated_ids = self.model.generate(
+            input_ids=input_ids,
+            num_beams=num_beams,
+            max_length=max_length,
+            repetition_penalty=repetition_penalty,
+            length_penalty=length_penalty,
+            early_stopping=early_stopping,
+            top_p=top_p,
+            top_k=top_k,
+            num_return_sequences=num_return_sequences,
+            do_sample = do_sample
+        )
+        preds = [
+            self.tokenizer.decode(
+                g,
+                skip_special_tokens=skip_special_tokens,
+                clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            )
+            for g in generated_ids
+        ]
+        return preds

requirements.txt

@@ -0,0 +1,2 @@
+torch
+transformers