|
--- |
|
language: |
|
- zh |
|
pipeline_tag: text-classification |
|
--- |
|
以ChatGLM2-6B作为基座模型再训练。 |
|
对文本进行情感分析。 |
|
|
|
加载代码: |
|
```python |
|
!git clone https://huggingface.co/Jerome2046/glm-emotion |
|
|
|
import torch |
|
import os |
|
from transformers import AutoConfig, AutoModel, AutoTokenizer |
|
|
|
# 载入Tokenizer与模型 |
|
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True) |
|
config = AutoConfig.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True, pre_seq_len=128) |
|
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", config=config, trust_remote_code=True) |
|
# 载入预训练参数 |
|
prefix_state_dict = torch.load(os.path.join("glm-emotion", "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.half().cuda().eval() |
|
|
|
response, history = model.chat(tokenizer, "说出'到北京五环25分钟车程,938离我住处只有300米,饮食一条街更是北京饮食街的翻版'此文段表达的情绪类型", history=[]) |
|
print(response) |
|
``` |