Update README.md

README.md

@@ -40,7 +40,47 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="sharad461/OpenWiseyak-0.1-MixedSFT-Adapter",
+    max_seq_length=2048,
+    dtype=None,
+    load_in_4bit=True,
+)
+
+FastLanguageModel.for_inference(model) 
+
+prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+question = ["यो वाक्यमा सर्वनाम कुन हो?", "श्यामको सुनको औठी हरायो र उ रोयो।", ""]
+
+inputs = tokenizer(prompt.format(
+    question[0],
+    question[1],
+    question[2],
+), return_tensors="pt").to("cuda")
+
+
+outputs = model.generate(**inputs, max_new_tokens=512, use_cache=True) 
+
+decoded_outputs = tokenizer.batch_decode(outputs)
+
+response = decoded_outputs[0].split("### Response:")[1].split("<|end_of_text|>")[0].strip()
+
+print(response)
+
+>>> वाक्यमा सर्वनाम "उ" हो, किनकि यो एक व्यक्तिगत सर्वनाम हो जसले श्यामलाई जनाउँछ।
+```
 
 [More Information Needed]