lime-1b

# Example usage
# pip install -U ukraine

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "anarlavrenov/LIME-1b"
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

def build_prompt(question):
  uid = "<user>"
  aid = "<assistant>"
  return uid + question + aid

question = "Write five questions for a Data Scientist interview."
prompt = build_prompt(question)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
input_length = inputs['input_ids'].shape[1]

outputs = model.generate(
    **inputs,
    max_new_tokens=128,
    num_beams=4,
    early_stopping=True,
    repetition_penalty=1.15,
    no_repeat_ngram_size=3,
    min_new_tokens=16,
    do_sample=False,
    top_p=None,
    temperature=None,
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
)

generated_tokens = outputs[0][input_length:]
output = tokenizer.decode(generated_tokens, skip_special_tokens=True)

print(output)

# 1. Can you tell us about your experience with data analysis and modeling? 
# 2. How do you approach data cleaning and preprocessing? 
# 3. How do you approach data visualization and storytelling? 
# 4. Can you walk us through a time when you used data to solve a problem? 
# 5. How do you approach the ethical considerations of data science and machine learning?