from transformers import AutoConfig, AutoModel, AutoTokenizer
import os
import torch

# 载入Tokenizer
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
config = AutoConfig.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True, pre_seq_len=128)
model = AutoModel.from_pretrained("THUDM/chatglm-6b", config=config, trust_remote_code=True)
prefix_state_dict = torch.load(os.path.join("./Adjust_ChatGLM_6B/", "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)
model = model.quantize(4)
model = model.half().cuda()
model.transformer.prefix_encoder.float()
model = model.eval()

response, history = model.chat(tokenizer, "生成衬衣的广告词", history=[])
print(response)
Downloads last month
10
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.