ChatGLM3 是智谱AI和清华大学 KEG 实验室联合发布的新一代对话预训练模型。ChatGLM3-6B 是 ChatGLM3 系列中的开源模型,在保留了前两代模型对话流畅、部署门槛低等众多优秀特性的基础上,ChatGLM3-6B 引入了如下特性:
**更强大的基础模型:**ChatGLM3-6B-Base 具有在 10B 以下的基础模型中最强的性能。
Model | GSM8K | MATH | BBH | MMLU | C-Eval | CMMLU | MBPP | AGIEval |
---|---|---|---|---|---|---|---|---|
ChatGLM2-6B-Base | 32.4 | 6.5 | 33.7 | 47.9 | 51.7 | 50.0 | - | - |
Best Baseline(10B 以下) | 52.1 | 13.1 | 45.0 | 60.1 | 63.5 | 62.2 | 47.5 | 45.8 |
ChatGLM3-6B-Base | 72.3 | 25.7 | 66.1 | 61.4 | 69.0 | 67.5 | 52.4 | 53.7 |
Model | 平均 | Summary | Single-Doc QA | Multi-Doc QA | Code | Few-shot | Synthetic |
---|---|---|---|---|---|---|---|
ChatGLM2-6B-32K | 41.5 | 24.8 | 37.6 | 34.7 | 52.8 | 51.3 | 47.7 |
ChatGLM3-6B-32K | 50.2 | 26.6 | 45.8 | 46.1 | 56.2 | 61.2 | 65 |
更完整的功能支持: ChatGLM3-6B 采用了全新设计的Prompt 格式。
更全面的开源序列:
Model | Seq Length | Download |
---|---|---|
ChatGLM3-6B | 8k | HuggingFace | ModelScope |
ChatGLM3-6B-Base | 8k | HuggingFace | ModelScope |
ChatGLM3-6B-32K | 32k | HuggingFace | ModelScope |
from modelscope import AutoTokenizer, AutoModel, snapshot_download
model_dir = snapshot_download("ZhipuAI/chatglm3-6b", revision = "master")
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModel.from_pretrained(model_dir, trust_remote_code=True).half().cuda()
model = model.eval()
response, history = model.chat(tokenizer, "你好", history=[])
print(response)
response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
print(response)
import os
import platform
from transformers import AutoTokenizer, AutoModel
model_path = "model/chatglm3_32k/"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True).cuda()
# 多显卡支持,使用下面两行代替上面一行,将num_gpus改为你实际的显卡数量
# from utils import load_model_on_gpus
# model = load_model_on_gpus(model_path, num_gpus=2)
model = model.eval()
os_name = platform.system()
clear_command = 'cls' if os_name == 'Windows' else 'clear'
stop_stream = False
welcome_prompt = "欢迎使用 ChatGLM3-6B 模型,输入内容即可进行对话,clear 清空对话历史,stop 终止程序"
def build_prompt(history):
prompt = welcome_prompt
for query, response in history:
prompt += f"\n\n用户:{query}"
prompt += f"\n\nChatGLM3-6B:{response}"
return prompt
def main():
past_key_values, history = None, []
global stop_stream
print(welcome_prompt)
while True:
query = input("\n用户:")
if query.strip() == "stop":
break
if query.strip() == "clear":
past_key_values, history = None, []
os.system(clear_command)
print(welcome_prompt)
continue
print("\nChatGLM:", end="")
current_length = 0
for response, history, past_key_values in model.stream_chat(tokenizer, query, history=history,temperature=1,
past_key_values=past_key_values,
return_past_key_values=True):
if stop_stream:
stop_stream = False
break
else:
print(response[current_length:], end="", flush=True)
current_length = len(response)
print(history)
print("")
# print(past_key_values)
if __name__ == "__main__":
main()