add app.py int4 cpu model and stream show

app.py

@@ -1,39 +1,104 @@
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoModel, AutoTokenizer
 import gradio as gr
+import mdtex2html
 
-# tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
-# model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
-# chatglm-6b-int4 cuda，本地可以运行成功
-# tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
-# model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").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()
+tokenizer = AutoTokenizer.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="")
+model = AutoModel.from_pretrained("models/chatglm-6b-int4", trust_remote_code=True, revision="").float()
 
+model = model.eval()
 
-# chatglm-6b-int4 CPU，
-tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
-model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").float()
+"""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
 
-# chatglm-6b
-# kernel_file = "./models/chatglm-6b-int4/quantization_kernels.so"
-# tokenizer = AutoTokenizer.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="")
-# model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
-# model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").float()
 
+gr.Chatbot.postprocess = postprocess
 
 
-# model = model.quantize(bits=model_args.quantization_bit, kernel_file=kernel_file)
+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
 
-model = model.eval()
 
+def predict(input, chatbot, max_length, top_p, temperature, history):
+ chatbot.append((parse_text(input), ""))
+ 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 [], []
+
+
+with gr.Blocks() as demo:
+ gr.HTML("""<h1 align="center">ChatGLM</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, 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([])
 
-def chat(msg):
- history = []
- response, history = model.chat(tokenizer, msg, history=history)
- print("response:", response)
- return response
+ 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)
 
-iface = gr.Interface(fn=chat, inputs="text", outputs="text")
-iface.launch()
+demo.queue().launch(share=False, inbrowser=True)

app_local.py

@@ -1,36 +1,104 @@
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoModel, AutoTokenizer
 import gradio as gr
+import mdtex2html
 
+# tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+# model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
 tokenizer = AutoTokenizer.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="")
-model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half()
-# model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
+model = AutoModel.from_pretrained(".\\models\\chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
 
+model = model.eval()
 
-# from transformers import AutoTokenizer, AutoModel
-# tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-# model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-# model = model.eval()
+"""Override Chatbot.postprocess"""
 
 
-# kernel_file = "./models/chatglm-6b-int4/quantization_kernels.so"
-# tokenizer = AutoTokenizer.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="")
-# model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").half().cuda()
-# model = AutoModel.from_pretrained("./models/chatglm-6b-int4", trust_remote_code=True, revision="").float()
+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
 
-# model = model.quantize(bits=model_args.quantization_bit, kernel_file=kernel_file)
 
-model = model.eval()
+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), ""))
+ 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 [], []
+
+
+with gr.Blocks() as demo:
+ gr.HTML("""<h1 align="center">ChatGLM</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, 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([])
 
-def chat(msg):
- history = []
- response, history = model.chat(tokenizer, msg, history=history)
- print("response:", response)
- return response
+ 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)
 
-iface = gr.Interface(fn=chat, inputs="text", outputs="text")
-iface.launch()
+demo.queue().launch(share=False, inbrowser=True)