# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ian-14/model_test", trust_remote_code=True, dtype="auto")Quick Links
How to use
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).half().cuda()
model = model.eval()
text = "你好"
response, history = model.chat(tokenizer, text, history=[])
response
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ian-14/model_test", trust_remote_code=True)