Gemma chat demo firstcommit

App.py

@@ -0,0 +1,135 @@
+import random
+
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("google/gemma-2b-it")
+isShowName = False
+
+
+def format_prompt(message, history):
+    prompt = ""
+    if history:
+        for user_prompt, bot_response in history:
+            prompt += f"<start_of_turn>user{user_prompt}<end_of_turn>"
+            prompt += f"<start_of_turn>model{bot_response}"
+    prompt += f"<start_of_turn>user{message}<end_of_turn><start_of_turn>model"
+    return prompt
+
+
+def generate(prompt, history, temperature=0.7, max_new_tokens=1024, top_p=0.90, repetition_penalty=0.9):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    if not history:
+        history = []
+
+    rand_seed = random.randint(1, 1111111111111111)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=rand_seed,
+    )
+
+    formatted_prompt = format_prompt(prompt, history)
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True,
+                                    return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        yield output
+    history.append((prompt, output))
+    return output
+
+
+def upload_file(inputs):
+    if not inputs:
+        return "No files provided", ""
+
+    file = inputs[0]  # Assuming you want to process only the first file if multiple are provided
+    print(f'FilePath:{inputs}')
+    filename = "D:/Develop/Python/GemmaChat/test.txt"
+    file_content = ""
+    if filename.endswith('.txt'):
+        try:
+            with open(filename, 'r', encoding='utf-8') as file:
+                file_content = file.read()
+        except FileNotFoundError:
+            return f"File not found: {filename}", ""
+        except PermissionError:
+            return f"Permission error: {filename}", ""
+        except FileNotFoundError:
+            return f"FileNotFoundError error: {filename}", ""
+        except UnicodeDecodeError:
+            return f"Error decoding file: {filename}. Please check the file encoding.", ""
+
+    return filename, file_content
+
+
+mychatbot = gr.Chatbot(
+    avatar_images=["./user.png", "./chatAI.svg"], bubble_full_width=False, show_label=False, show_copy_button=True,
+    likeable=True, )
+
+additional_inputs = [
+    gr.Slider(
+        label="Temperature",
+        value=0.7,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.01,
+        interactive=True,
+        info="更高的价值产生更多样化的产出",
+    ),
+    gr.Slider(
+        label="Max new tokens",
+        value=6400,
+        minimum=0,
+        maximum=8000,
+        step=64,
+        interactive=True,
+        info="新令牌的最大数量",
+    ),
+    gr.Slider(
+        label="Top-p",
+        value=0.90,
+        minimum=0.0,
+        maximum=1,
+        step=0.01,
+        interactive=True,
+        info="较高的值代表更多的低概率标记",
+    ),
+    gr.Slider(
+        label="Repetition penalty",
+        value=1.0,
+        minimum=0.1,
+        maximum=2.0,
+        step=0.1,
+        interactive=True,
+        info="对重复令牌进行处罚",
+    )
+]
+
+iface = gr.ChatInterface(fn=generate,
+                         chatbot=mychatbot,
+                         additional_inputs=additional_inputs,
+                         retry_btn=None,
+                         undo_btn=None
+                         )
+
+with gr.Blocks() as demo:
+    gr.HTML("<center><h1>Yang's Chat with Google's Gemma</h1></center>")
+    iface.render()
+    with gr.Tab(label="Text"):
+        upload_button = gr.File(label="File")
+    with gr.Tab(label="Image"):
+        image = gr.Image(label="图片")
+
+demo.queue().launch(show_api=False)

README.md

@@ -1,13 +1,13 @@
----
-title: GemmaChat
-emoji: 📚
-colorFrom: gray
-colorTo: green
+title: Gemma Chat
+emoji: ✨
+colorFrom: green
+colorTo: purple
 sdk: gradio
 sdk_version: 4.19.2
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+models:
+- google/gemma-2b-it
+- google/gemma-2b
+- google/gemma-7b-it
+- google/gemma-7b
+  app_file: app.py
+  pinned: false

requirements.txt

@@ -0,0 +1,2 @@
+gradio~=4.19.1
+huggingface_hub~=0.20.3