jekunz's picture
Update README.md
aeddbb2 verified
metadata
library_name: transformers
license: apache-2.0
datasets:
  - HuggingFaceFW/fineweb-2
language:
  - fo
base_model:
  - HuggingFaceTB/SmolLM2-135M-Instruct
pipeline_tag: text-generation

This is a SmolLM2-135M-Instruct model fine-tuned first on the Icelandic and then on the Faroese portion of Fineweb-2. It is intended for my research and has not been evaluated more broadly yet.

Training:

  • 1 Epoch Icelandic, 5 Epochs Faroese
  • Learning rate: 5e-4
  • LR scheduler: Cosine
  • Warmup ratio: 0.05
  • Batch size: 1
  • 4 A100 (40GB) GPUs
  • Gradient accumulation steps: 64
  • Effective batch size: 256
  • Max. context length: 8192 tokens