llama3-7b-en-ar – AI Model by The-CoLab | AlphaNeural AI

You can deploy this model and start earning money today!

The-CoLab/
llama3-7b-en-ar

like

0

Views

No views yet

llama3-7b-en-ar

LLaMA-3 7B pretrained on English-Arabic bilingual data, ~42k steps.

Validation Results

Final checkpoint: step 41,416

Validation set	Cross-entropy loss (nats)	Perplexity
English (en)	2.5379	12.65
AR (`ar`)	3.3761	29.26

Note: Validation losses measured at step 41,416 (last validate before step-42000 checkpoint).

Evaluation Results

EEE-format evaluation results are stored under eval_results/eee/ in this repository. Tasks: Global MMLU (EN/AR/RU), PIQA, ECLeKTic, Fictive Entity (2-rate mix).

Citation

Part of the The-CoLab multilingual-transfer collection.