Update README.md

README.md

@@ -13,5 +13,28 @@ license: other
 
 # LLäMmlein 1B
 
-This is a Bavarian adapter for the German Tinyllama 1B language model which was tuned on a dump of the Bavarian wikipedia.
-Find more details on our [page](https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/) and our [preprint](arxiv.org/abs/2411.11171)!
+This is a Bavarian adapter for the German Tinyllama 1B language model which was tuned on a dump of the Bavarian wikipedia, without further optimization. Please don't take it too seriously ;)
+Find more details on our [page](https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/) and our [preprint](arxiv.org/abs/2411.11171)!
+
+## Run it
+```py
+import torch
+from peft import PeftConfig, PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# script config
+base_model_name = "LSX-UniWue/LLaMmlein_1B"
+chat_adapter_name = "LSX-UniWue/Betzerl_1B_wiki_preview"
+device = "cuda"  # or mps
+
+# load model
+config = PeftConfig.from_pretrained(chat_adapter_name)
+base_model = model = AutoModelForCausalLM.from_pretrained(
+    base_model_name,
+    torch_dtype=torch.bfloat16,
+    device_map=device,
+)
+base_model.resize_token_embeddings(32064)
+model = PeftModel.from_pretrained(base_model, chat_adapter_name)
+tokenizer = AutoTokenizer.from_pretrained(chat_adapter_name)
+```