Downloads · 30 days
0
Anonymous-Repo/armt-gemma-3-1b-it-8x1024-lora-babilong-qa1-5
armt-gemma-3-1b-it-8x1024-lora-babilong-qa1-5 is a machine learning model from Anonymous-Repo. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
ARMT model based on gemma-3-1b-it and finetuned on QA1-5 tasks from BABILong up to 8k.
Downloads · 30 days
0
Access
Public
Updated Nov 18, 2025
Repo size
2.2 GB
Likes
0
Public
Click a slice to open those files.
.bin2.2 GB · 100%
From the Hugging Face model README
ARMT model based on gemma-3-1b-it and finetuned on QA1-5 tasks from BABILong up to 8k.
Scores on BABILong, QA1-QA5:
| Len | QA1 | QA2 | QA3 | QA4 | QA5 |
|---|---|---|---|---|---|
| 0k | 100 | 100 | 98 | 100 | 99 |
| 1k | 100 | 99 | 99 | 100 | 99 |
| 2k | 100 | 99 | 98 | 91 | 99 |
| 4k | 100 | 98 | 94 | 89 | 99 |
| 8k | 99 | 97 | 90 | 96 | 99 |
| 16k | 100 | 89 | 77 | 99 | 99 |
| 32k | 100 | 87 | 75 | 98 | 97 |
| 64k | 99 | 86 | 65 | 97 | 96 |