Upload folder using huggingface_hub

api.py

@@ -50,7 +50,7 @@ async def create_item(request: Request):
 
 
 if __name__ == '__main__':
-    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-    model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+    model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
     model.eval()
     uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)

cli_demo.py

@@ -4,8 +4,8 @@ import signal
 from transformers import AutoTokenizer, AutoModel
 import readline
 
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 model = model.eval()
 
 os_name = platform.system()

web_demo.py

@@ -2,8 +2,8 @@ from transformers import AutoModel, AutoTokenizer
 import gradio as gr
 import mdtex2html
 
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 model = model.eval()
 
 """Override Chatbot.postprocess"""
@@ -98,4 +98,4 @@ with gr.Blocks() as demo:
 
     emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
 
-demo.queue().launch(share=True, inbrowser=True)
+demo.queue().launch(share=False, inbrowser=True)

web_demo_old.py

@@ -1,101 +1,45 @@
 from transformers import AutoModel, AutoTokenizer
 import gradio as gr
-import mdtex2html
 
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 model = model.eval()
 
-"""Override Chatbot.postprocess"""
+MAX_TURNS = 20
+MAX_BOXES = MAX_TURNS * 2
 
 
-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):
-    chatbot.append((parse_text(input), ""))
+def predict(input, max_length, top_p, temperature, history=None):
+    if history is None:
+        history = []
     for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
                                                temperature=temperature):
-        chatbot[-1] = (parse_text(input), parse_text(response))       
-
-        yield chatbot, history
-
-
-def reset_user_input():
-    return gr.update(value='')
-
-
-def reset_state():
-    return [], []
+        updates = []
+        for query, response in history:
+            updates.append(gr.update(visible=True, value="用户：" + query))
+            updates.append(gr.update(visible=True, value="ChatGLM-6B：" + response))
+        if len(updates) < MAX_BOXES:
+            updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
+        yield [history] + updates
 
 
 with gr.Blocks() as demo:
-    gr.HTML("""<h1 align="center">ChatGLM</h1>""")
+    state = gr.State([])
+    text_boxes = []
+    for i in range(MAX_BOXES):
+        if i % 2 == 0:
+            text_boxes.append(gr.Markdown(visible=False, label="提问："))
+        else:
+            text_boxes.append(gr.Markdown(visible=False, label="回复："))
 
-    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")
+            txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", lines=11).style(
+                container=False)
         with gr.Column(scale=1):
-            emptyBtn = gr.Button("Clear History")
             max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
             top_p = gr.Slider(0, 1, value=0.7, 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([])
-
-    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
-                    show_progress=True)
-    submitBtn.click(reset_user_input, [], [user_input])
-
-    emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
-
-demo.queue().launch(share=True, inbrowser=True)
+            button = gr.Button("Generate")
+    button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes)
+demo.queue().launch(share=False, inbrowser=True)