Downloads · 30 days
94
49% of all-time downloads
MoraxGeo/Sherry-1B-1.25bit-per-group
Sherry-1B-1.25bit-per-group is a machine learning model from MoraxGeo. 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 llama3.2.
A reproduced 1.25bit 1B model based on LLaMA-3.2 with Sherry quantization method from the paper: Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
Downloads · 30 days
94
49% of all-time downloads
All-time downloads
191
Public
Parameters
1.2B
2.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors2.5 GB · 99%
From the Hugging Face model README
A reproduced 1.25bit 1B model based on LLaMA-3.2 with Sherry quantization method from the paper:
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
[0.0315, 0.0000, 0.0315, -0.0315, -0.0315, -0.0315, 0.0000, 0.0315]| Model | Size | Quant type | ARC_C | ARC_E | HelS | PIQA | WinG | AVG |
|---|---|---|---|---|---|---|---|---|
| LLaMA3.2 | 1B | - | 0.313 | 0.654 | 0.477 | 0.742 | 0.603 | 0.558 |
| Sherry (reported in paper) | 1B | per-channel | - | - | - | - | - | 0.513 |
| Sherry (reproduced) | 1B | per-channel | 0.297 | 0.618 | 0.386 | 0.707 | 0.560 | 0.514 |
| Sherry (reported in paper) | 1B | per-group | 0.309 | 0.647 | 0.388 | 0.699 | 0.550 | 0.519 |
| Sherry (reproduced) | 1B | per-group | 0.292 | 0.648 | 0.390 | 0.706 | 0.556 | 0.518 |
| LLaMA3.2 | 3B | - | 0.422 | 0.745 | 0.552 | 0.768 | 0.691 | 0.636 |
| Sherry (reported in paper) | 3B | per-group | 0.364 | 0.688 | 0.452 | 0.736 | 0.593 | 0.567 |
| Sherry (reproduced) | 3B | per-channel | 0.360 | 0.713 | 0.445 | 0.732 | 0.596 | 0.569 |