Update README.md

README.md

@@ -3,17 +3,20 @@ library_name: transformers
 language:
 - fi
 ---
+## Model description
 
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-Instruct finetuned model from https://huggingface.co/Finnish-NLP/llama-7b-finnish for 2 epochs using 11014 samples combined from following sources:
+This is an early v0.1 version release of our Instruct finetuned model from https://huggingface.co/Finnish-NLP/llama-7b-finnish
+Model was trained for 2 epochs using 11014 samples and for this release we chose checkpoint at 2500/4048 steps.
+
+For finetuning we used mix of following datasources:
 LIMA from https://github.com/TurkuNLP/finnish-instructions
 Dolly from https://github.com/TurkuNLP/finnish-instructions
 OASST from https://github.com/TurkuNLP/finnish-instructions
 Heavily filtered version of Ultrachat + deepl translations from https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized/viewer/default/train_sft
 
 
+
 ### How to use
 
 Here is an example of using this model with Unsloth with some generation arguments you can modify:
@@ -123,9 +126,9 @@ VASTAUS:
 
 ### Limitations and bias
 
-The training data used for this model contains a lot of content from the internet, which is far from neutral. Therefore, the model can have biased predictions. This bias will also affect all fine-tuned versions of this model.
-
-To reduce toxic content, training data was filtered with a toxicity classifier but it cannot truly eliminate all toxic text.
+The training data used for this model contains a lot of content from the internet, which is far from neutral. 
+Therefore, the model can have biased predictions. This bias will also affect all fine-tuned versions of this model.
+To reduce toxic content, the pretrained version of thiis model was trained with dataset filtered with a toxicity classifier but it cannot truly eliminate all toxic text.
 
 ### Finetuning