Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- en
+- fi
 license: apache-2.0
 tags:
 - text-generation-inference
@@ -9,15 +9,20 @@ tags:
 - llama
 - trl
 - sft
-base_model: mpasila/Viking-33B-1000B
+base_model: LumiOpen/Viking-33B
+datasets:
+- mpasila/Finnish-ShareGPT-Tiny-V1-1
 ---
+Uses my [tiny dataset](https://huggingface.co/datasets/mpasila/Finnish-ShareGPT-Tiny-V1-1) to train this bigger variant of Viking model family.
+
+This LoRA uses the 1000B checkpoint.
 
 # Uploaded  model
 
 - **Developed by:** mpasila
 - **License:** apache-2.0
-- **Finetuned from model :** mpasila/Viking-33B-1000B
+- **Finetuned from model :** LumiOpen/Viking-33B
 
 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)