import torch
from transformers import LlamaTokenizerFast, AutoModelForCausalLM

model_name = "jordiclive/scaled-llama-7b-lora-16k-rp2"


model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,trust_remote_code=True
)
tokenizer = LlamaTokenizerFast.from_pretrained(
        model_name)


tokenizer.model_max_length = 16384
tokenizer.pad_token = tokenizer.eos_token
model.max_sequence_length = tokenizer.model_max_length