丹摩智算：探索Llama3.1模型的部署与使用

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import streamlit as st

# 创建一个标题和一个副标题
st.title("💬 LLaMA3.1 Chatbot")
st.caption("🚀 A streamlit chatbot powered by Self-LLM")

# 定义模型路径
mode_name_or_path = '/root/workspace/Llama-3.1-8B-Instruct'

# 定义一个函数，用于获取模型和tokenizer
@st.cache_resource
def get_model():
    tokenizer = AutoTokenizer.from_pretrained(mode_name_or_path, trust_remote_code=True)
    tokenizer.pad_token = tokenizer.eos_token
    model = AutoModelForCausalLM.from_pretrained(mode_name_or_path, torch_dtype=torch.bfloat16).cuda()
    return tokenizer, model

# 加载LLaMA3的model和tokenizer
tokenizer, model = get_model()

# 如果session_state中没有"messages"，则创建一个包含默认消息的列表
if "messages" not in st.session_state:
    st.session_state["messages"] = []

# 遍历session_state中的所有消息，并显示在聊天界面上
for msg in st.session_state.messages:
    st.chat_message(msg["role"]).write(msg["content"])

# 如果用户在聊天输入框中输入了内容，则执行以下操作
if prompt := st.chat_input():
    # 在聊天界面上显示用户的输入
    st.chat_message("user").write(prompt)
    # 将用户输入添加到session_state中的messages列表中
    st.session_state.messages.append({"role": "user", "content": prompt})
    # 将对话输入模型，获得返回
    input_ids = tokenizer.apply_chat_template(st.session_state["messages"],tokenize=False,add_generation_prompt=True)
    model_inputs = tokenizer([input_ids], return_tensors="pt").to('cuda')
    generated_ids = model.generate(model_inputs.input_ids,max_new_tokens=512)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    # 将模型的输出添加到session_state中的messages列表中
    st.session_state.messages.append({"role": "assistant", "content": response})
    # 在聊天界面上显示模型的输出
    st.chat_message("assistant").write(response)
    print(st.session_state)

streamlit run llamaBot.py --server.address 0.0.0.0 --server.port 1024