Update README.md

README.md

@@ -25,5 +25,23 @@ Dataset from [Workshop for NLP introduction with Spanish jokes](https://github.c
 
 ## How to use
 ```py
-# TODO
+import torch
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+peft_model_id = "mrm8488/bertin-gpt-j-6B-es-finetuned-chistes_spanish_jokes-500"
+config = PeftConfig.from_pretrained(peft_model_id)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto')
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# Load the Lora model
+model = PeftModel.from_pretrained(model, peft_model_id)
+
+# Inference
+batch = tokenizer("Esto son dos amigos", return_tensors='pt')
+
+with torch.cuda.amp.autocast():
+  output_tokens = model.generate(**batch, max_new_tokens=50)
+
+print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))
 ```