inite eyeoyon

app.py

@@ -1,64 +1,34 @@
+# transformersとtorch、Gradioをインポート
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 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")
+# トークナイザーとモデルをロードする
+tokenizer = AutoTokenizer.from_pretrained("eyepyon/rcphi2")
+model = AutoModelForCausalLM.from_pretrained("eyepyon/rcphi2")
+
+# txt入力を受け取り、それを使用して新しいtxtを生成する関数
+def generate(prompt):
+    # 入力テキストをトークナイズ
+    inputs = tokenizer.encode(prompt, return_tensors='pt')
+    # トークナイズされたテキストを使用して新しいテキストを生成
+    outputs = model.generate(inputs, max_length=300, temperature=1.0, top_k=50, top_p=0.95, do_sample=True)
+    # 生成されたテキストをデコード
+    predicted_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # デコードされたテキストを関数から返す
+    return predicted_text
+
+# Gradio UIを作成
+iface = gr.Interface(
+    # 上記で定義したテキスト生成関数を使用
+    generate,
+    # 入力としてテキストボックスを使用
+    inputs = gr.Textbox(label = "Input a question", default = "質問してください"),
+    # 出力はテキスト形式
+    outputs="text",
+    # UIのタイトル設定
+    title = "Mr Bot🤖")
+
+# Gradio UIを起動
+iface.launch()
 
-
-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
-"""
-demo = gr.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()

appORG.py

@@ -0,0 +1,64 @@
+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
+"""
+demo = gr.ChatInterface(
+    respond,
+    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)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -1 +1,6 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+
+tensorflow
+transformers
+torch
+sentencepiece