Views
No views yet
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained(
4 "vuiseng9/llama2-7b-fused-qkv",
5 trust_remote_code=True
6)
7tokenizer = AutoTokenizer.from_pretrained("vuiseng9/llama2-7b-fused-qkv")
8
9inputs = tokenizer("Hello, I'm", return_tensors="pt")
10outputs = model.generate(**inputs, max_length=50)
11print(tokenizer.decode(outputs[0]))