Update README.md

README.md

@@ -106,6 +106,11 @@ print(generated_text)
 ```
 
 # unsloth Train examples
+```bash
+python3 -m venv Llama-3.1-Nemotron-Nano-Train
+source Llama-3.1-Nemotron-Nano-Train/bin/activate
+pip install unsloth
+```
 
 ```python
 from unsloth import FastLanguageModel
@@ -118,7 +123,7 @@ load_in_4bit = True  # Use 4-bit quantization to reduce memory usage
 
 # Load the pre-trained model and tokenizer
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name="./Llama-3.1-Nemotron-Nano-8B-v1-bnb-4bit",  # Local path to the model
+    model_name="aifeifei798/Llama-3.1-Nemotron-Nano-8B-v1-bnb-4bit",  # Local path to the model
     max_seq_length=max_seq_length,
     dtype=dtype,
     load_in_4bit=load_in_4bit,