Update README.md

README.md

@@ -8,7 +8,7 @@ language:
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
-malhajar/Llama-2-13b-chat-dolly-tr is a finetuned version of Llama-2-7b-hf using SFT Training.
+malhajar/Llama-2-13b-chat-dolly-tr is a finetuned version of Llama-2-13b-hf using SFT Training.
 This model can answer information in turkish language as it is finetuned on a turkish dataset specifically [`databricks-dolly-15k-tr`]( https://huggingface.co/datasets/atasoglu/databricks-dolly-15k-tr) 
 
 ![llama](./llama.png)
@@ -31,7 +31,7 @@ Use the code sample provided in the original post to interact with the model.
 ```python
 from transformers import AutoTokenizer,AutoModelForCausalLM
  
-model_id = "malhajar/Llama-2-13b-chat-dolly-tr"
+model_id = "malhajar/Llama-2-7b-chat-dolly-tr"
 model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                              device_map="auto",
                                              torch_dtype=torch.float16,
@@ -39,17 +39,15 @@ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-question: "what is the will to truth?"
+question: "Türkiyenin en büyük şehir nedir?"
 # For generating a response
 prompt = '''
-### Instruction:
-{question} 
-
-### Response:'''
+<s>[INST] {question}  [/INST]
+'''
 input_ids = tokenizer(prompt, return_tensors="pt").input_ids
 output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokenizer.eos_token_id,top_k=50, do_sample=True,repetition_penalty=1.3
         top_p=0.95)
 response = tokenizer.decode(output[0])
 
 print(response)
-```
+```