Update README.md

README.md

@@ -21,3 +21,42 @@ language:
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+
+# How to use
+
+```Python
+
+def load_model(model_name):
+  # QLoRA config
+  bnb_config = BitsAndBytesConfig(
+      load_in_4bit=True,
+      bnb_4bit_quant_type="nf4",
+      bnb_4bit_compute_dtype=torch.bfloat16,
+      bnb_4bit_use_double_quant=False,
+  )
+
+  # Load model
+  model = AutoModelForCausalLM.from_pretrained(
+      model_name,
+      quantization_config=bnb_config,
+      device_map="auto",
+      token=HF_TOKEN
+  )
+
+  # Load tokenizer
+  tokenizer = AutoTokenizer.from_pretrained(
+      model_name,
+      trust_remote_code=True,
+      token=HF_TOKEN
+  )
+  return model, tokenizer
+
+
+model_name = "ak0327/llm-jp-3-13b-ft-5"
+
+model, tokenizer = load_model(model_name)
+datasets = load_test_datasets()
+results = inference(model_name, datasets, model, tokenizer)
+```
+