llk010502's picture
Create README.md
2c4a79c verified
|
raw
history blame
451 Bytes

Inference

from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

model = "meta-llama/Llama-2-7b-chat-hf"

tokenizer = AutoTokenizer.from_pretrained(model, trust_remote_code=True)

model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True, device_map = 'cuda')
model = PeftModel.from_pretrained(model, "FinGPT/fingpt-forecaster_sz50_llama2-7B_lora")

model = model.eval()