Update app.py

app.py

@@ -1,63 +1,110 @@
+
+from transformers import AutoModel, AutoTokenizer
 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()
+import mdtex2html
+#from utils import load_model_on_gpus
+
+tokenizer = AutoTokenizer.from_pretrained("sethuiyer/Medichat-Llama3-8B", trust_remote_code=True)
+#model = AutoModel.from_pretrained("sethuiyer/Medichat-Llama3-8B", trust_remote_code=True).cuda()
+model = AutoModel.from_pretrained("sethuiyer/Medichat-Llama3-8B", trust_remote_code=True)
+# 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
+# from utils import load_model_on_gpus
+# model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)
+model = model.eval()
+
+"""Override Chatbot.postprocess"""
+
+
+def postprocess(self, y):
+    if y is None:
+        return []
+    for i, (message, response) in enumerate(y):
+        y[i] = (
+            None if message is None else mdtex2html.convert((message)),
+            None if response is None else mdtex2html.convert(response),
+        )
+    return y
+
+
+gr.Chatbot.postprocess = postprocess
+
+
+def parse_text(text):
+    """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
+    lines = text.split("\n")
+    lines = [line for line in lines if line != ""]
+    count = 0
+    for i, line in enumerate(lines):
+        if "```" in line:
+            count += 1
+            items = line.split('`')
+            if count % 2 == 1:
+                lines[i] = f'<pre><code class="language-{items[-1]}">'
+            else:
+                lines[i] = f'<br></code></pre>'
+        else:
+            if i > 0:
+                if count % 2 == 1:
+                    line = line.replace("`", "\`")
+                    line = line.replace("<", "&lt;")
+                    line = line.replace(">", "&gt;")
+                    line = line.replace(" ", "&nbsp;")
+                    line = line.replace("*", "&ast;")
+                    line = line.replace("_", "&lowbar;")
+                    line = line.replace("-", "&#45;")
+                    line = line.replace(".", "&#46;")
+                    line = line.replace("!", "&#33;")
+                    line = line.replace("(", "&#40;")
+                    line = line.replace(")", "&#41;")
+                    line = line.replace("$", "&#36;")
+                lines[i] = "<br>"+line
+    text = "".join(lines)
+    return text
+
+
+def predict(input, chatbot, max_length, top_p, temperature, history, past_key_values):
+    chatbot.append((parse_text(input), ""))
+    for response, history, past_key_values in model.stream_chat(tokenizer, input, history, past_key_values=past_key_values,
+                                                                return_past_key_values=True,
+                                                                max_length=max_length, top_p=top_p,
+                                                                temperature=temperature):
+        chatbot[-1] = (parse_text(input), parse_text(response))
+
+        yield chatbot, history, past_key_values
+
+
+def reset_user_input():
+    return gr.update(value='')
+
+
+def reset_state():
+    return [], [], None
+
+
+with gr.Blocks() as demo:
+    gr.HTML("""<h1 align="center">ChatGLM2-6B</h1>""")
+
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        with gr.Column(scale=4):
+            with gr.Column(scale=12):
+                user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
+                    container=False)
+            with gr.Column(min_width=32, scale=1):
+                submitBtn = gr.Button("Submit", variant="primary")
+        with gr.Column(scale=1):
+            emptyBtn = gr.Button("Clear History")
+            max_length = gr.Slider(0, 32768, value=8192, step=1.0, label="Maximum length", interactive=True)
+            top_p = gr.Slider(0, 1, value=0.8, step=0.01, label="Top P", interactive=True)
+            temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
+
+    history = gr.State([])
+    past_key_values = gr.State(None)
+
+    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history, past_key_values],
+                    [chatbot, history, past_key_values], show_progress=True)
+    submitBtn.click(reset_user_input, [], [user_input])
+
+    emptyBtn.click(reset_state, outputs=[chatbot, history, past_key_values], show_progress=True)
+
+demo.queue().launch(server_name="0.0.0.0",server_port=7860,share=False, inbrowser=True)