demo_single_chat.py

from transformers import AutoTokenizer, AutoModel
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()

# tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
# model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)



kernel_file = "./models/chatglm-6b-int4/quantization_kernels.so"
model = model.quantize(bits=4, kernel_file=kernel_file)
model = model.eval()

def parse_text(text):
    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
response_new = ''
history = []
for chatbot, history in  predict('请写一篇1000字的散文', chatbot=[], max_length=10000, top_p=0.5, temperature=0.5, history=history):
    response_old = response_new
    response_new = chatbot[0][1]
    new_single = response_new.replace(response_old, '')
    print(new_single,end='')