mistral-7b-text-to-sql

• This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the b-mc2/sql-create-context dataset.
• These are the adapter weights, and the code to use these for generation is given below.
• A full model will be uploaded at a later date.
• Primary reference: https://www.philschmid.de/fine-tune-llms-in-2024-with-trl

Model description

• Model type: Language model
• Language(s) (NLP): English
• License: Apache 2.0
• Finetuned from model : Mistral-7B-v0.1

How to get started with the model

import torch
from transformers import AutoTokenizer, pipeline
from datasets import load_dataset
from peft import AutoPeftModelForCausalLM
from random import randint

peft_model_id = "delayedkarma/mistral-7b-text-to-sql"

# Load Model with PEFT adapter
model = AutoPeftModelForCausalLM.from_pretrained(
  peft_model_id,
  device_map="auto",
  torch_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
# load into pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

# Load dataset and Convert dataset to OAI messages
system_message = """You are a text to SQL query translator. Users will ask you questions in English and you will generate a SQL query based on the provided SCHEMA.
SCHEMA:
{schema}"""

def create_conversation(sample):
  return {
    "messages": [
      {"role": "system", "content": system_message.format(schema=sample["context"])},
      {"role": "user", "content": sample["question"]},
      {"role": "assistant", "content": sample["answer"]}
    ]
  }

# Load dataset from the hub
dataset = load_dataset("b-mc2/sql-create-context", split="train")
dataset = dataset.shuffle().select(range(100))

# Convert dataset to OAI messages
dataset = dataset.map(create_conversation, remove_columns=dataset.features, batched=False)

dataset = dataset.train_test_split(test_size=20/100)

# Evaluate
eval_dataset = dataset['test']
rand_idx = randint(0, len(eval_dataset))

# Test on sample
prompt = pipe.tokenizer.apply_chat_template(eval_dataset[rand_idx]["messages"][:2], tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=False, temperature=0.1, top_k=50, top_p=0.1, eos_token_id=pipe.tokenizer.eos_token_id, pad_token_id=pipe.tokenizer.pad_token_id)

print(f"Query:\n{eval_dataset[rand_idx]['messages'][1]['content']}")
print(f"Original Answer:\n{eval_dataset[rand_idx]['messages'][2]['content']}")
print(f"Generated Answer:\n{outputs[0]['generated_text'][len(prompt):].strip()}")

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 3
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 6
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Framework versions

• PEFT 0.7.2.dev0
• Transformers 4.36.2
• Pytorch 2.2.2
• Datasets 2.16.1
• Tokenizers 0.15.2