[!NOTE] This is a copy of jekunz/smollm-135m-lora-fineweb-faroese at commit
e55c7de, made on 2026-10-30. vLLM CI uses this checkpoint and the original is on a personal account, so we keep a copy here to reduce supply-chain risk.
This model is a SmolLM2-135M-Instruct model fine-tuned on the Faroese portion of Fineweb-2. It is intended for my research and has not been evaluated more broadly yet.
LoRA setup:
- Rank: 256
- Alpha: 512
- Target modules: ["up_proj", "down_proj", "gate_proj", "o_proj"]
Training:
- 5 Epochs
- Learning rate: 8e-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