Update README.md

README.md

@@ -82,5 +82,53 @@ response = tokenizer.batch_decode(outputs)
 
 
 
+# Inference With Inference with HuggingFace transformers
+
+
+
+
+```python3
+
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "Xhaheen/Shaheen_Gemma_Urdu_",
+    load_in_4bit = False
+)
+tokenizer = AutoTokenizer.from_pretrained("Xhaheen/Shaheen_Gemma_Urdu_")
+
+
+input_prompt = """
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+
+
+input_text = input_prompt.format(
+        "دیئے گئے موضوع کے بارے میں ایک مختصر پیراگراف لکھیں۔", # instruction
+        "قابل تجدید توانائی کے استعمال کی اہمیت", # input
+        "", # output - leave this blank for generation!
+    )
+
+inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")
+
+outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)
+response = tokenizer.batch_decode(outputs)[0]
+
+```
+
+
+
+
+
+
+
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)