Upload README.md

README.md

@@ -85,16 +85,6 @@ model, tokenizer = FastLanguageModel.from_pretrained(
     # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
 )
 
-if False:
-    from unsloth import FastLanguageModel
-    model, tokenizer = FastLanguageModel.from_pretrained(
-        model_name = "Llama-3.2-1B-Instruct-bnb-4bit-lora", # YOUR MODEL YOU USED FOR TRAINING
-        max_seq_length = max_seq_length,
-        dtype = dtype,
-        load_in_4bit = load_in_4bit,
-    )
-    FastLanguageModel.for_inference(model) # Enable native 2x faster inference
-
 # alpaca_prompt = You MUST copy from above!
 
 inputs = tokenizer(
@@ -120,8 +110,7 @@ from transformers import TextStreamer
 text_streamer = TextStreamer(tokenizer)
 _ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 1024)
 
-#model.save_pretrained_merged("Llama-3.2-1B-Instruct-bnb-4bit-end", tokenizer)
-                   
+                  
 ```
 
 ### Trainer Prograpm