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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support