import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "openlm-research/open_llama_3b_600bt_preview"
fast_model_name = "danielhanchen/open_llama_3b_600bt_preview"

tokenizer = AutoTokenizer.from_pretrained(fast_model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype = torch.float16, device_map = "auto")

prompt = "Q: What is the largest animal?\nA:"
input_ids = tokenizer(prompt, return_tensors = "pt").input_ids
print( tokenizer.decode( model.generate( input_ids, max_new_tokens = 32).ravel() ) )

# from huggingface_hub import notebook_login
# notebook_login()
from transformers import LlamaTokenizerFast
from tokenizers import AddedToken
tokenizer = LlamaTokenizerFast.from_pretrained(
    "openlm-research/open_llama_3b_600bt_preview",
    add_bos_token = True,
    add_eos_token = False, # Original LLaMA is False -> add </s> during processing.
    bos_token = AddedToken("<s>",   single_word = True),
    eos_token = AddedToken("</s>",  single_word = True),
    unk_token = AddedToken("<unk>", single_word = True),
    pad_token = AddedToken("<unk>", single_word = True)
)
tokenizer.push_to_hub("open_llama_3b_600bt_preview")