Update README.md

README.md

@@ -61,11 +61,20 @@ This is a work in progress. I plan to continue the fine-tuning process with bett
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
 
-model_name = "Aleton/qwen3-belarusian"
+peft_model_id = "Aleton/qwen3-belarusian" 
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+config = PeftConfig.from_pretrained(peft_model_id)
+
+model = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path, 
+    device_map="auto",
+    trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+model = PeftModel.from_pretrained(model, peft_model_id)
 
 prompt = "Прывітанне! Распавядзі мне пра Беларусь."
 messages = [
@@ -73,22 +82,11 @@ messages = [
     {"role": "user", "content": prompt}
 ]
 
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
-
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 
-generated_ids = model.generate(
-    model_inputs.input_ids,
-    max_new_tokens=512
-)
-
-generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-]
+generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
+generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)]
 
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)