rakeshkiriyath/gpt2Medium_text_to_sql
527
Model Card
<!-- The base model used for training is gpt2-medium. We finetuned it on the following dataset: b-mc2/sql-create-context -->
This is my first fine tuned LLM project.
Usage
from transformers import GPT2LMHeadModel, GPT2Tokenizer
finetunedGPT = GPT2LMHeadModel.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
finetunedTokenizer = GPT2Tokenizer.from_pretrained("rakeshkiriyath/gpt2Medium_text_to_sql")
def generate_text_to_sql(query, model, tokenizer, max_length=256):
prompt = f"Translate the following English question to SQL: {query}"
input_tensor = tokenizer.encode(prompt, return_tensors='pt').to('cuda')
output = model.generate(input_tensor, max_length=max_length, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
# Return only the SQL part (removing the input text)
sql_output = decoded_output[len(prompt):].strip()
return sql_output
queryList = ["I need a list of employees who joined in the company last 6 months with a salary hike of 30% ",
"Give me loginid,status,company of a user who is mapped to the organization XYZ "]
for query in queryList:
sql_result = generate_text_to_sql(query, finetunedGPT, finetunedTokenizer)
print(sql_result,"\n")
Output
SELECT COUNT(*) FROM employees WHERE last6months = "6 months" AND salaryhike = "30%" \ SELECT loginid,status,company FROM usermappedtoorganization WHERE mapping = "XYZ"
Training Hyperparameters
numtrainepochs=1 \ perdevicetrainbatchsize=3 \ gradientaccumulationsteps=9 \ learningrate=5e-5 \ weightdecay=0.01
Evaluation
{'evalloss': 0.23689331114292145, 'evalruntime': 104.4102, 'evalsamplespersecond': 67.043, 'evalstepspersecond': 8.38, 'epoch': 1.0}