Update README.md

README.md

@@ -35,4 +35,39 @@ AryaBhatta-GemmaOrca      35.9       72.26   53.85       40.35       50.59 \
 zephyr-7b-beta	          37.52	     71.77	 55.26	     39.77	     51.08 \
 zephyr-7b-gemma-v0.1	  34.22	     66.37	 52.19	     37.10	     47.47 \
 mlabonne/Gemmalpaca-7B	  21.6	     40.87	 44.85	     30.49	     34.45 \
-google/gemma-7b-it	      21.33	     40.84	 41.70	     30.25	     33.53 
+google/gemma-7b-it	      21.33	     40.84	 41.70	     30.25	     33.53 
+
+
+
+How to use:-
+
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "GenVRadmin/AryaBhatta-GemmaOrca",
+    load_in_4bit = False,
+    token = hf_token
+)
+tokenizer = AutoTokenizer.from_pretrained("GenVRadmin/AryaBhatta-GemmaOrca")
+
+input_prompt = """
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+input_text = input_prompt.format(
+        "Answer this question about India.", # instruction
+        "Who is the Prime Minister of India", # 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]