|
--- |
|
base_model: unsloth/Llama-3.2-1B |
|
language: |
|
- en |
|
- 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. |
|
|
|
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:** 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) |
