Fix inference code

README.md

@@ -1,3 +1,22 @@
 ---
 license: cc-by-nc-4.0
 ---
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "OdiaGenAI/odiagenAI_llama7b_base_v1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code = True)
+prompt = "ଭାରତ ବିଷୟରେ କିଛି କୁହନ୍ତୁ"
+inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model = AutoModelForCausalLM.from_pretrained(model_id).to(device)
+
+outputs = model.generate(inputs, max_new_tokens=100)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```