|
import torch |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig |
|
|
|
base_model_id= "google/gemma-2b" |
|
bnb_config = BitsAndBytesConfig( |
|
load_in_4bit=True, |
|
bnb_4bit_use_double_quant=True, |
|
bnb_4bit_quant_type="nf4", |
|
bnb_4bit_compute_dtype=torch.bfloat16 |
|
) |
|
|
|
base_model = AutoModelForCausalLM.from_pretrained( |
|
base_model_id, |
|
quantization_config=bnb_config, |
|
device_map="auto", |
|
trust_remote_code=True, |
|
) |
|
|
|
eval_tokenizer = AutoTokenizer.from_pretrained(base_model_id, add_bos_token=True, trust_remote_code=True) |
|
|
|
|
|
from peft import PeftModel |
|
|
|
ft_model = PeftModel.from_pretrained(base_model, "./gemma-jokes-gemma/checkpoint-150") |
|
|
|
|
|
eval_prompt = "why can't Barbie get pregnant" |
|
|
|
model_input = eval_tokenizer(eval_prompt, return_tensors="pt").to("cuda:0") |
|
|
|
ft_model.eval() |
|
with torch.no_grad(): |
|
print(eval_tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=100, repetition_penalty=1.15)[0], skip_special_tokens=True)) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|