Downloads · 30 days
12
21% of all-time downloads
The-CoLab/llama3-7b-en-ru-v2
llama3-7b-en-ru-v2 is a machine learning model from The-CoLab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.
LLaMA-3 7B pretrained on English-Russian bilingual data, 134k steps (injection fix v2).
Downloads · 30 days
12
21% of all-time downloads
All-time downloads
56
Public
Parameters
6.3B
12.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors12.6 GB · 100%
From the Hugging Face model README
LLaMA-3 7B pretrained on English-Russian bilingual data, 134k steps (injection fix v2).
Final checkpoint: step 133,600
| Validation set | Cross-entropy loss (nats) | Perplexity |
|---|---|---|
| English (en) | 2.2403 | 9.40 |
RU (ru) | 0.7749 | 2.17 |
Note: Rerun with corrected injection config (Buckwalter transliteration fix + injection count fix). Training proceeded in two LSF jobs: the first (step 38,000–72,501) was restarted due to a node issue; the second continuation (step ~74,010–133,600) ran cleanly to completion. The final validation losses above are from step 133,600 of the continuation job. An earlier intermediate checkpoint at step 70,808 had EN=1.273 / RU=0.941 (reported in a prior version of this card).
EEE-format evaluation results are stored under eval_results/eee/ in this repository.
Tasks: Global MMLU (EN/RU), PIQA, ECLeKTic, Fictive Entity (2-rate mix).
Per-step training and validation loss curves are stored in training_curves/:
| File | Description |
|---|---|
train_loss.csv | Training loss every 10 steps (step,train_loss) — covers the continuation phase (~steps 42,500–133,600) |
val_loss.csv | Validation loss per language (step,lang,val_loss) — 90 rows, steps 74,816–133,600 (continuation phase) |
Part of the The-CoLab multilingual-transfer collection.