Multilingual-Transfer
Collection
Pretraining models to find what allows multilingual transfer • 26 items • Updated • 2
llama3-7b-en-ar-134k
LLaMA-3 7B pretrained on English-Arabic bilingual data, 134k steps.
Validation Results
Final checkpoint: step 133,600
| Validation set | Cross-entropy loss (nats) | Perplexity |
|---|---|---|
| English (en) | 2.2676 | 9.66 |
AR (ar) |
2.8828 | 17.86 |
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.
- Downloads last month
- 30
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support