import os, sys import gradio as gr import mdtex2html import torch import transformers from transformers import ( AutoConfig, AutoModel, AutoTokenizer, AutoTokenizer, DataCollatorForSeq2Seq, HfArgumentParser, Seq2SeqTrainingArguments, set_seed, ) from arguments import ModelArguments, DataTrainingArguments model = None tokenizer = None """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) def main(): global model, tokenizer parser = HfArgumentParser(( ModelArguments)) if len(sys.argv) == 2 and sys.argv[1].endswith(".json"): # If we pass only one argument to the script and it's the path to a json file, # let's parse it to get our arguments. model_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))[0] else: model_args = parser.parse_args_into_dataclasses()[0] tokenizer = AutoTokenizer.from_pretrained( model_args.model_name_or_path, trust_remote_code=True) config = AutoConfig.from_pretrained( model_args.model_name_or_path, trust_remote_code=True) config.pre_seq_len = model_args.pre_seq_len config.prefix_projection = model_args.prefix_projection if model_args.ptuning_checkpoint is not None: print(f"Loading prefix_encoder weight from {model_args.ptuning_checkpoint}") model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True) prefix_state_dict = torch.load(os.path.join(model_args.ptuning_checkpoint, "pytorch_model.bin")) new_prefix_state_dict = {} for k, v in prefix_state_dict.items(): if k.startswith("transformer.prefix_encoder."): new_prefix_state_dict[k[len("transformer.prefix_encoder."):]] = v model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict) else: model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True) if model_args.quantization_bit is not None: print(f"Quantized to {model_args.quantization_bit} bit") model = model.quantize(model_args.quantization_bit) if model_args.pre_seq_len is not None: # P-tuning v2 model = model.half().cuda() model.transformer.prefix_encoder.float().cuda() model = model.eval() demo.queue().launch(share=False, inbrowser=True) if __name__ == "__main__": main()