Update README.md

README.md

@@ -2,21 +2,29 @@
 base_model: unsloth/Llama-3.2-1B
 language:
 - en
-license: apache-2.0
+- fi
+license: llama3.2
 tags:
 - text-generation-inference
 - transformers
 - unsloth
 - llama
 - trl
+datasets:
+- wikimedia/wikipedia
 ---
+Here's a "continued pre-trained" model using [Finnish Wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset. I still don't understand why no one in Finland has figured out that they could just do continued pre-training on existing models that are already supported by every frontend.. I've seen Japanese models perform pretty well with that kind of continued pre-training, yet Finnish models are still done from scratch which means they suck ass. If you compare them to Llama 3 or Gemma 2 they just suck so much. They can't even match Mistral 7B a model from last year. Just stop wasting money on training models from scratch, use these better models as base and train it on all your closed-source data I don't have access to. Thank you.
 
-# Uploaded  model
+Merged model: [mpasila/Llama-3.2-Finnish-Wikipedia-1B](https://huggingface.co/mpasila/Llama-3.2-Finnish-Wikipedia-1B)
+
+Trained with regular LoRA (not quantized/QLoRA) and LoRA rank was 128 and Alpha set to 32. Trained for 1 epoch using RTX 4090 for about 12,5 hours.
+
+# Uploaded Llama-3.2-Finnish-Wikipedia-LoRA-1B model
 
 - **Developed by:** mpasila
-- **License:** apache-2.0
+- **License:** Llama 3.2 Community License Agreement
 - **Finetuned from model :** unsloth/Llama-3.2-1B
 
 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)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)