Update README.md

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
 library_name: peft
 model_name: Llama-3.2-1B-it-Medical-LoRA
 tags:
@@ -8,6 +9,11 @@ tags:
 - trl
 - sft
 licence: license
+license: mit
+datasets:
+- tmnam20/ViMedAQA
+language:
+- vi
 ---
 
 # Model Card for Llama-3.2-1B-it-Medical-LoRA
@@ -20,7 +26,22 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
  
 This model was trained with SFT.
 
-## Inference Usage
+## Usage
+
+### HuggingFace Authentication
+```python
+import os
+from huggingface_hub import login
+
+# Set the Hugging Face API token
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = "<your_huggingface_token>"
+
+# # Initialize API
+login(os.environ.get("HUGGINGFACEHUB_API_TOKEN"))
+```
+
+### Inference
+
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline