AIAT/Optimizer-sealion2pandas

  from transformers import AutoModelForCausalLM, AutoTokenizer
  import pandas as pd
  
  tokenizer = AutoTokenizer.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)
  model = AutoModelForCausalLM.from_pretrained("AIAT/Optimizer-sealion2pandas", trust_remote_code=True)

  df = pd.read_csv("Your csv..")
  
  prompt_template = "### USER:\n{human_prompt}\n\n### RESPONSE:\n"
  
  prompt = """\
  You are working with a pandas dataframe in Python. 
  The name of the dataframe is `df`.
  This is the result of `print(df.head())`:
  {df_str}
  
  Follow these instructions: 
  1. Convert the query to executable Python code using Pandas. 
  2. The final line of code should be a Python expression that can be called with the `eval()` function.
  3. The code should represent a solution to the query.
  4. PRINT ONLY THE EXPRESSION.
  5. Do not quote the expression.
  Query: {query_str} """
  
  def create_prompt(query_str, df):
      text = prompt.format(df_str=str(df.head()), query_str=query_str)
      text = prompt_template.format(human_prompt=text)
      return text
  
  full_prompt = create_prompt("Find test ?", df)

  tokens = tokenizer(full_prompt, return_tensors="pt")
  output = model.generate(tokens["input_ids"], max_new_tokens=20, eos_token_id=tokenizer.eos_token_id)
  print(tokenizer.decode(output[0], skip_special_tokens=True))