Update README.md

README.md

@@ -38,7 +38,7 @@ This is quantized adapters trained on the Ultrachat 200k dataset for the TinyLla
 
 ### How to use
 
-#### Method 1: Direct loading
+#### Method 1: Direct loading via AutoPeftModel
 ```python
 from peft import PeftModel, AutoPeftModelForCausalLM
 from transformers import pipeline, AutoTokenizer
@@ -60,11 +60,8 @@ pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer)
 print(pipe(prompt)[0]["generated_text"])
 
 ```
-#### Method 2: Merging with base mode explicitly
-todo
 
-
-### Method 3: direct loading 
+### Method 2: direct loading AutoModel
 
 ```python
 model = AutoModelForCausalLM.from_pretrained(adapter_name,
@@ -78,4 +75,8 @@ Tell me something about Large Language Models.</s>
 
 pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer)
 print(pipe(prompt)[0]["generated_text"])
-```
+```
+
+#### Method 2: Merging with base mode explicitly
+todo
+