RichardErkhov/mpasila_-_Llama-3.2-Finnish-Wikipedia-1B-gguf
0440
Quantization made by Richard Erkhov.
Llama-3.2-Finnish-Wikipedia-1B - GGUF
- Model creator: https://huggingface.co/mpasila/
- Original model: https://huggingface.co/mpasila/Llama-3.2-Finnish-Wikipedia-1B/
Original model description: --- base_model: unsloth/Llama-3.2-1B language:
- en
- fi license: llama3.2 tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft datasets:
- wikimedia/wikipedia --- Here's a "continued pre-trained" model using Finnish 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.
LoRA: mpasila/Llama-3.2-Finnish-Wikipedia-LoRA-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.
So it does have some issues but I could try training it on Gemma 2 2B and see if that's a better model for this (Gemma 2 already is better at Finnish than Llama 3) and maybe add more datasets containing Finnish.
Evaluation
FIN-bench scores:
Uploaded Llama-3.2-Finnish-Wikipedia-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 and Huggingface's TRL library.