Update README.md

README.md

@@ -1,5 +1,32 @@
 LoRA which is fine-tuned for "command" following.
 
+### How to use?
+
+
+    import torch
+    from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+
+    model_id = "EleutherAI/pythia-2.8b-deduped"
+
+    bnb_config = BitsAndBytesConfig(
+        load_in_4bit=True,
+        bnb_4bit_use_double_quant=True,
+        bnb_4bit_quant_type="nf4",
+        bnb_4bit_compute_dtype=torch.bfloat16
+    )
+
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
+
+    # load adapter
+    if True:
+        from peft import PeftModel
+        model = PeftModel.from_pretrained(
+            model, "Q4234/commandA-LoRA-2.8b",
+            torch_dtype=torch.float16
+        )
+
+
 ### Prompting
 
     Assistant can use any tools he likes by calling the tool as python functions.