Update app.py

app.py

@@ -1,63 +1,81 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+import spaces
+
+# 言語リスト
+languages = [
+    "English", "Chinese (Simplified)", "Chinese (Traditional)", "Spanish", "Arabic", "Hindi",
+    "Bengali", "Portuguese", "Russian", "Japanese", "German", "French", "Urdu", "Indonesian",
+    "Italian", "Turkish", "Korean", "Vietnamese", "Tamil", "Marathi", "Telugu", "Persian",
+    "Polish", "Dutch", "Thai", "Gujarati", "Romanian", "Ukrainian", "Malay", "Kannada", "Oriya (Odia)",
+    "Burmese (Myanmar)", "Azerbaijani", "Uzbek", "Kurdish (Kurmanji)", "Swedish", "Filipino (Tagalog)",
+    "Serbian", "Czech", "Hungarian", "Greek", "Belarusian", "Bulgarian", "Hebrew", "Finnish",
+    "Slovak", "Norwegian", "Danish", "Sinhala", "Croatian", "Lithuanian", "Slovenian", "Latvian",
+    "Estonian", "Armenian", "Malayalam", "Georgian", "Mongolian", "Afrikaans", "Nepali", "Pashto",
+    "Punjabi", "Kurdish", "Kyrgyz", "Somali", "Albanian", "Icelandic", "Basque", "Luxembourgish",
+    "Macedonian", "Maltese", "Hawaiian", "Yoruba", "Maori", "Zulu", "Welsh", "Swahili", "Haitian Creole",
+    "Lao", "Amharic", "Khmer", "Javanese", "Kazakh", "Malagasy", "Sindhi", "Sundanese", "Tajik", "Xhosa",
+    "Yiddish", "Bosnian", "Cebuano", "Chichewa", "Corsican", "Esperanto", "Frisian", "Galician", "Hausa",
+    "Hmong", "Igbo", "Irish", "Kinyarwanda", "Latin", "Samoan", "Scots Gaelic", "Sesotho", "Shona",
+    "Sotho", "Swedish", "Uyghur"
+]
+
+tokenizer = AutoTokenizer.from_pretrained("aixsatoshi/Honyaku-7b-v2")
+model = AutoModelForCausalLM.from_pretrained("aixsatoshi/Honyaku-7b-v2", torch_dtype=torch.float16)
+model = model.to('cuda:0')
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [2]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+@spaces.GPU
+def predict(message, history, tokens, temperature, language):
+    tag = "<" + language.lower() + ">"
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\n<english>:"+item[0]+"</english>\n", tag+item[1]])
+                for item in history_transformer_format])
+
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=int(tokens),
+        temperature=float(temperature),
+        do_sample=True,
+        top_p=0.95,
+        top_k=20,
+        repetition_penalty=1.15,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    partial_message = ""
+    for new_token in streamer:
+        if new_token != '<':
+            partial_message += new_token
+            yield partial_message
+
+# Gradioインタフェースの設定
 demo = gr.ChatInterface(
-    respond,
+    fn=predict, 
+    title="Honyaku-7b webui",
+    description="Translate using Honyaku-7b model",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+        gr.Slider(100, 4096, value=1000, label="Tokens"),
+        gr.Slider(0.0, 1.0, value=0.3, label="Temperature"),
+        gr.Dropdown(choices=languages, value="Japanese", label="Language")
+    ]
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+demo.queue().launch()