Update README.md

README.md

@@ -3,4 +3,31 @@ library_name: peft
 base_model: autopilot-ai/Indic-sentence-completion
 ---
 
-Low Rank Adapter for Bloom decoder for grammar correction.
+Low Rank Adapter for Bloom decoder for grammar correction.
+
+# Example Usage:
+    import torch
+    from peft import PeftModel, PeftConfig
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    from IPython.display import display, Markdown
+
+    peft_model_id = "Jayveersinh-Raj/bloom-sentence-correction"
+    config = PeftConfig.from_pretrained(peft_model_id)
+    model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=False, device_map='auto')
+    tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+    # Load the Lora model
+    qa_model = PeftModel.from_pretrained(model, peft_model_id)
+
+
+
+    def make_inference(question):
+       batch = tokenizer(f"### INCORRECT\n{question}\n\n### CORRECT\n", return_tensors='pt').to("cuda")
+
+       with torch.cuda.amp.autocast():
+         output_tokens = qa_model.generate(**batch, max_new_tokens=200)
+
+       display(Markdown((tokenizer.decode(output_tokens[0], skip_special_tokens=True))))
+
+    text = "I red a book last night"
+    make_inference(text)