Update README.md

README.md

@@ -6,6 +6,24 @@ language:
 
 # Cabrita: portuguese instructLLaMA
 
+## Usage
+
+Check the Github repo with code: https://github.com/22-hours/cabrita
+
+```
+from peft import PeftModel
+from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig
+
+tokenizer = LLaMATokenizer.from_pretrained("decapoda-research/llama-7b-hf")
+model = LLaMAForCausalLM.from_pretrained(
+    "decapoda-research/llama-7b-hf",
+    load_in_8bit=True,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(model, "22h/cabrita-lora-v0-1")
+```
+
+
 ## Data
 
 We translated the [alpaca_data.json](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json) to portuguese using ChatGPT. Even if this translation was not the best, the tradeoff between costs and results were. We paid around US$ 8.00 to translate the full dataset to portuguese.