Update README.md

README.md

@@ -32,3 +32,86 @@ The following `bitsandbytes` quantization config was used during training:
 - PEFT 0.5.0
 
 - PEFT 0.5.0
+#  Inference Code
+
+### Install required libraries
+
+```python
+!pip install transformers peft
+```
+### Login
+```python
+from huggingface_hub import login
+
+token = "Your Key"
+login(token)
+```
+#### Import necessary modules
+```python
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from transformers import BitsAndBytesConfig
+from peft import prepare_model_for_kbit_training
+```
+#### Load PEFT model and configuration
+```python
+config = PeftConfig.from_pretrained("Shreyas45/Llama2_Text-to-SQL_Fintuned")
+peft_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
+peft_model = PeftModel.from_pretrained(peft_model, "Shreyas45/Llama2_Text-to-SQL_Fintuned")
+```
+### Load trained model and tokenizer
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from peft import prepare_model_for_kbit_training
+
+trained_model_tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)
+trained_model_tokenizer.pad_token = trained_model_tokenizer.eos_token
+```
+
+### Define a SQL query
+```python
+query = '''In the table named management with columns (department_id VARCHAR, temporary_acting VARCHAR); 
+            CREATE TABLE department (name VARCHAR, num_employees VARCHAR, department_id VARCHAR), 
+            Show the name and number of employees for the departments managed by heads whose temporary acting value is 'Yes'?'''
+```
+
+### Construct prompt
+```python
+prompt = f'''### Instruction: Below is an instruction that describes a task and the schema of the table in the database. 
+            Write a response that generates a request in the form of a SQL query. 
+            Here the schema of the table is mentioned first followed by the question for which the query needs to be generated. 
+            And the question is: {query}
+###Output: '''
+```
+### Tokenize the prompt
+```python
+encodings = trained_model_tokenizer(prompt, return_tensors='pt')
+```
+#### Configure generation parameters
+```python
+
+generation_config = peft_model.generation_config
+generation_config.max_new_token = 1024
+generation_config.temperature = 0.7
+generation_config.top_p = 0.7
+generation_config.num_return_sequence = 1
+generation_config.pad_token_id = trained_model_tokenizer.pad_token_id
+generation_config.eos_token_id = trained_model_tokenizer.eos_token_id
+```
+### Generate SQL query using the model
+```python
+with torch.inference_mode():
+    outputs = peft_model.generate(
+        input_ids=encodings.input_ids,
+        attention_mask=encodings.attention_mask,
+        generation_config=generation_config,
+        max_new_tokens=100
+    )
+```
+### Decode and print the generated SQL query
+```python
+generated_query = trained_model_tokenizer.decode(outputs[0])
+print("Generated SQL Query:")
+print(generated_query)
+```