ChatGLM 6b int4 g32 quantization

已过时 Deprecated：使用新的 ChatGLM2 模型

See K024/chatglm-q for more details.

import torch
from chatglm_q.decoder import ChatGLMDecoder, chat_template

device = torch.device("cuda")
decoder = ChatGLMDecoder.from_pretrained("K024/chatglm-6b-int4g32", device=device)

prompt = chat_template([], "我是谁？")
for text in decoder.generate(prompt):
    print(text)

Model weights are released under the same license as ChatGLM-6b, see MODEL LICENSE.