YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
amharic-clean-lora
Public checkpoint mirror for the take-2 Amharic fine-tuning (clean conversational mix,
Gemma-4 E4B + rasyosef Llama-3.2-1B-Amharic). Trained by
asr-lab/scripts/finetune_amharic.py on Kaggle T4 x2 with Unsloth QLoRA.
Layout: <run>/checkpoint-<step>/ and <run>/final_lora/ (e.g. e4b_clean/,
1b_clean/). Resume target for continued / distillation runs.
Plan: asr-lab/finetuning_plans_2.md.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support