Update README.md

README.md

@@ -26,19 +26,20 @@ This project is for research purposes only. Third-party datasets may be subject
 ## How to Get Started with the Model
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-You need to merge the adapter with the base model and infer it using PEFT or Unsloth library.
+You can infer the adapters directly using Peft/Unsloth library or you can merge the adapter with the base model and can use it.
 Please find an example below using Unsloth:
 
-```
+```python
 import torch
 from unsloth import FastLanguageModel
 from transformers import AutoTokenizer, pipeline
 model_id='FinLang/investopedia_chat_model'
 max_seq_length=2048
 model, tokenizer = FastLanguageModel.from_pretrained(
-        model_name = "anamikac2708/Llama3-8b-finetuned-investopedia-Merged-FP16", # YOUR MODEL YOU USED FOR TRAINING
+        model_name = "anamikac2708/Llama3-8b-finetuned-investopedia-Lora-Adapters", # YOUR MODEL YOU USED FOR TRAINING
         max_seq_length = max_seq_length,
-        dtype = torch.bfloat16
+        dtype = torch.bfloat16,
+        load_in_4bit = False #Make it True if you want to use bitsandbytes 4bit
     )
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)