From 6148d6d6ac41a416846df1ebfa9b1341a1f69859 Mon Sep 17 00:00:00 2001 From: tuteng0915 Date: Mon, 3 Apr 2023 23:11:31 +0800 Subject: [PATCH 1/7] add web_demo3 --- .gitignore | 133 +++++++++++++++++++++++++++++++++++++++++++++++ requirements.txt | 1 + web_demo3.py | 69 ++++++++++++++++++++++++ 3 files changed, 203 insertions(+) create mode 100644 .gitignore create mode 100644 web_demo3.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 00000000..c3dd476a --- /dev/null +++ b/.gitignore @@ -0,0 +1,133 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +pip-wheel-metadata/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST +history/ + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +.python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# Mac system file +model/ \ No newline at end of file diff --git a/requirements.txt b/requirements.txt index 00707fe7..072d12c6 100644 --- a/requirements.txt +++ b/requirements.txt @@ -4,3 +4,4 @@ icetk cpm_kernels torch>=1.10 gradio +mdtex2html \ No newline at end of file diff --git a/web_demo3.py b/web_demo3.py new file mode 100644 index 00000000..d6a62ec3 --- /dev/null +++ b/web_demo3.py @@ -0,0 +1,69 @@ +from transformers import AutoModel, AutoTokenizer +import gradio as gr +from typing import TYPE_CHECKING, Any, Callable, Dict, List, Tuple, Type +import mdtex2html + +tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) +model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).quantize(8).half().cuda() +model = model.eval() + +# MAX_TURNS = 20 +# MAX_BOXES = MAX_TURNS * 2 + +"""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 predict(input, chatbot, max_length, top_p, temperature, history): + chatbot.append((input, "")) + for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p, + temperature=temperature): + chatbot[-1] = (input, response) + yield chatbot, history + +def reset_user_input(): + return gr.update(value='') + + +def reset_state(): + return [], [] + +with gr.Blocks() as demo: + gr.HTML("""

ChatGLM

""") + + with gr.Row(): + with gr.Column(scale=4): + chatbot = gr.Chatbot() + with gr.Row(): + with gr.Column(scale=12): + user_input = gr.Textbox(show_label=False, placeholder="Input...").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([]) + + user_input.submit(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True) + user_input.submit(reset_user_input, [], [user_input]) + + 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=False, inbrowser=True) From ec069419becceac2d69a07149c07b9fc564e19db Mon Sep 17 00:00:00 2001 From: duzx16 Date: Mon, 3 Apr 2023 23:29:04 +0800 Subject: [PATCH 2/7] Add another web demo with Gradio --- web_demo3.py | 40 ++++++++++++++++++++++------------------ 1 file changed, 22 insertions(+), 18 deletions(-) diff --git a/web_demo3.py b/web_demo3.py index d6a62ec3..203ba1fd 100644 --- a/web_demo3.py +++ b/web_demo3.py @@ -4,22 +4,23 @@ import mdtex2html tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) -model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).quantize(8).half().cuda() +model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda() model = model.eval() -# MAX_TURNS = 20 -# MAX_BOXES = MAX_TURNS * 2 - """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 + 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 @@ -27,9 +28,10 @@ def predict(input, chatbot, max_length, top_p, temperature, history): chatbot.append((input, "")) for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p, temperature=temperature): - chatbot[-1] = (input, response) + chatbot[-1] = (input, response) yield chatbot, history + def reset_user_input(): return gr.update(value='') @@ -37,6 +39,7 @@ def reset_user_input(): def reset_state(): return [], [] + with gr.Blocks() as demo: gr.HTML("""

ChatGLM

""") @@ -54,16 +57,17 @@ def reset_state(): 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([]) - user_input.submit(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True) + user_input.submit(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], + show_progress=True) user_input.submit(reset_user_input, [], [user_input]) - submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True) + 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=False, inbrowser=True) +demo.queue().launch(share=True, inbrowser=True) From 119caa15ef98de6faf3c66e82fa900f9b21b505c Mon Sep 17 00:00:00 2001 From: tuteng0915 Date: Mon, 3 Apr 2023 23:31:30 +0800 Subject: [PATCH 3/7] add parse_text --- web_demo3.py | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) diff --git a/web_demo3.py b/web_demo3.py index d6a62ec3..80ffce97 100644 --- a/web_demo3.py +++ b/web_demo3.py @@ -23,11 +23,44 @@ def postprocess(self, y): gr.Chatbot.postprocess = postprocess +def parse_text(text): + """revise 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'
'
+            else:
+                lines[i] = f'
' + else: + if i > 0: + if count % 2 == 1: + line = line.replace("`", "\`") + line = line.replace("<", "<") + line = line.replace(">", ">") + line = line.replace(" ", " ") + line = line.replace("*", "*") + line = line.replace("_", "_") + line = line.replace("-", "-") + line = line.replace(".", ".") + line = line.replace("!", "!") + line = line.replace("(", "(") + line = line.replace(")", ")") + line = line.replace("$", "$") + lines[i] = "
"+line + text = "".join(lines) + return text + + def predict(input, chatbot, max_length, top_p, temperature, history): - chatbot.append((input, "")) + 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] = (input, response) + chatbot[-1] = (parse_text(input), parse_text(response)) yield chatbot, history def reset_user_input(): From d21f891a76e9df2da7d3e0f6e5c5d28ef1dde337 Mon Sep 17 00:00:00 2001 From: tuteng0915 Date: Mon, 3 Apr 2023 23:36:18 +0800 Subject: [PATCH 4/7] add parse_text --- web_demo3.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/web_demo3.py b/web_demo3.py index 80ffce97..ad5ba115 100644 --- a/web_demo3.py +++ b/web_demo3.py @@ -4,7 +4,7 @@ import mdtex2html tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) -model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).quantize(8).half().cuda() +model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda() model = model.eval() # MAX_TURNS = 20 @@ -24,7 +24,7 @@ def postprocess(self, y): def parse_text(text): - """revise from https://github.com/GaiZhenbiao/ChuanhuChatGPT/""" + """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/""" lines = text.split("\n") lines = [line for line in lines if line != ""] count = 0 From cc4be399ff1a88f5459b3b8793b83c4372409517 Mon Sep 17 00:00:00 2001 From: duzx16 Date: Thu, 6 Apr 2023 16:58:40 +0800 Subject: [PATCH 5/7] Update web demo3 --- web_demo3.py | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/web_demo3.py b/web_demo3.py index 7c0777c2..0e399681 100644 --- a/web_demo3.py +++ b/web_demo3.py @@ -1,10 +1,9 @@ from transformers import AutoModel, AutoTokenizer import gradio as gr -from typing import TYPE_CHECKING, Any, Callable, Dict, List, Tuple, Type 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("/mnt/vepfs/workspace/zxdu/chatglm_6b", trust_remote_code=True) +model = AutoModel.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm_6b", trust_remote_code=True).half().cuda() model = model.eval() """Override Chatbot.postprocess""" @@ -77,15 +76,14 @@ def reset_state(): with gr.Blocks() as demo: gr.HTML("""

ChatGLM

""") + chatbot = gr.Chatbot() with gr.Row(): with gr.Column(scale=4): - chatbot = gr.Chatbot() - with gr.Row(): - with gr.Column(scale=12): - user_input = gr.Textbox(show_label=False, placeholder="Input...").style( - container=False) - with gr.Column(min_width=32, scale=1): - submitBtn = gr.Button("Submit", variant="primary") + 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) @@ -94,10 +92,6 @@ def reset_state(): history = gr.State([]) - user_input.submit(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], - show_progress=True) - user_input.submit(reset_user_input, [], [user_input]) - submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history], show_progress=True) submitBtn.click(reset_user_input, [], [user_input]) From 40d83f32feb6fcbec54ab8c8479a4830378edb3e Mon Sep 17 00:00:00 2001 From: duzx16 Date: Thu, 6 Apr 2023 17:00:51 +0800 Subject: [PATCH 6/7] Update model path --- web_demo3.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/web_demo3.py b/web_demo3.py index 0e399681..df7f9833 100644 --- a/web_demo3.py +++ b/web_demo3.py @@ -2,8 +2,8 @@ import gradio as gr import mdtex2html -tokenizer = AutoTokenizer.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm_6b", trust_remote_code=True) -model = AutoModel.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm_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""" From 28335463394983ddfc7b554f8fd3ee894a7b98b5 Mon Sep 17 00:00:00 2001 From: duzx16 Date: Thu, 6 Apr 2023 17:01:24 +0800 Subject: [PATCH 7/7] Use chatbot web demo --- web_demo.py | 104 +++++++++++++++++++++++++++++++++++++----------- web_demo3.py | 101 ---------------------------------------------- web_demo_old.py | 45 +++++++++++++++++++++ 3 files changed, 125 insertions(+), 125 deletions(-) delete mode 100644 web_demo3.py create mode 100644 web_demo_old.py diff --git a/web_demo.py b/web_demo.py index 88a6dc88..df7f9833 100644 --- a/web_demo.py +++ b/web_demo.py @@ -1,45 +1,101 @@ 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() model = model.eval() -MAX_TURNS = 20 -MAX_BOXES = MAX_TURNS * 2 +"""Override Chatbot.postprocess""" -def predict(input, max_length, top_p, temperature, history=None): - if history is None: - history = [] +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'
'
+            else:
+                lines[i] = f'
' + else: + if i > 0: + if count % 2 == 1: + line = line.replace("`", "\`") + line = line.replace("<", "<") + line = line.replace(">", ">") + line = line.replace(" ", " ") + line = line.replace("*", "*") + line = line.replace("_", "_") + line = line.replace("-", "-") + line = line.replace(".", ".") + line = line.replace("!", "!") + line = line.replace("(", "(") + line = line.replace(")", ")") + line = line.replace("$", "$") + lines[i] = "
"+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): - 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 + 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: - 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：")) + gr.HTML("""

ChatGLM

""") + chatbot = gr.Chatbot() with gr.Row(): with gr.Column(scale=4): - txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", lines=11).style( - container=False) + 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) - button = gr.Button("Generate") - button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes) -demo.queue().launch(share=False, inbrowser=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) diff --git a/web_demo3.py b/web_demo3.py deleted file mode 100644 index df7f9833..00000000 --- a/web_demo3.py +++ /dev/null @@ -1,101 +0,0 @@ -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() -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'
'
-            else:
-                lines[i] = f'
' - else: - if i > 0: - if count % 2 == 1: - line = line.replace("`", "\`") - line = line.replace("<", "<") - line = line.replace(">", ">") - line = line.replace(" ", " ") - line = line.replace("*", "*") - line = line.replace("_", "_") - line = line.replace("-", "-") - line = line.replace(".", ".") - line = line.replace("!", "!") - line = line.replace("(", "(") - line = line.replace(")", ")") - line = line.replace("$", "$") - lines[i] = "
"+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("""

ChatGLM

""") - - 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([]) - - 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) diff --git a/web_demo_old.py b/web_demo_old.py new file mode 100644 index 00000000..88a6dc88 --- /dev/null +++ b/web_demo_old.py @@ -0,0 +1,45 @@ +from transformers import AutoModel, AutoTokenizer +import gradio as gr + +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() + +MAX_TURNS = 20 +MAX_BOXES = MAX_TURNS * 2 + + +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): + 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: + 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：")) + + with gr.Row(): + with gr.Column(scale=4): + txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", lines=11).style( + container=False) + with gr.Column(scale=1): + 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) + button = gr.Button("Generate") + button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes) +demo.queue().launch(share=False, inbrowser=True)