Update README.md

README.md

@@ -24,6 +24,42 @@ train/epoch : 5.0
 train/global_step : 10
 
 
+## Inference Code
+
+After doing necessary imports
+
+device_map = {"": 0}
+model_id = "mistralai/Mistral-7B-v0.1"
+new_model = "Akil15/mistral_SQL_v.0.1"
+
+# Reload model in FP16 and merge it with LoRA weights
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16,
+    device_map=device_map,
+)
+
+model = PeftModel.from_pretrained(base_model, new_model)
+model = model.merge_and_unload()
+
+# Reload tokenizer to save it
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = "right"
+
+sample text(example):
+
+text = """Question: How many vegetable farms with over 100 acres of cultivated land utilize organic farming methods, and what is the average yield per acre for these farms?
+Context:CREATE TABLE vegetable_farm (Acres INTEGER,Organic BOOLEAN,Yield_Per_Acre DECIMAL);"""
+
+text = input()
+inputs = tokenizer(text, return_tensors="pt").to(device)
+outputs = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+Note: Change the max_new_tokens length based on the question-context text input or just define it to 100 
+
 ### Framework versions