Downloads · 30 days
11
16% of all-time downloads
gemma-2-27b-FLUTE
radi-cho/gemma-2-27b-FLUTE
gemma-2-27b-FLUTE is a text generation model from radi-cho. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as gemma.
WARNING: gemma-2-27b models don't run well in float16 precision.<br This FLUTE-quantized model is released in bfloat16.
All-time downloads
70
Public
Parameters
8.1B
16.2 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16.2 GB · 100%
Parameter types
How the weights are stored.
I166.5B · 80%
Try a prompt
Model card
From the Hugging Face model README
WARNING: gemma-2-27b models don't run well in float16 precision.<br>
This FLUTE-quantized model is released in bfloat16.
| Wiki | C4 | PIQA | ARC-E | ARC-C | HellaSwag | Wino | Avg. | |
|---|---|---|---|---|---|---|---|---|
| Unquantized | 5.70 | 8.98 | 83.24 | 87.84 | 62.88 | 65.35 | 79.24 | 75.71 |
| W4G64 | 5.69 | 9.31 | 82.53 | 86.45 | 59.22 | 64.13 | 78.21 | 74.11 |
| W3G64 | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD |
Evaluations are provided for models with learned scales.<br>Benchmark scores (zero-shot) are computed with lm-evaluation-harness.
- Task
- Text Generation
- Library
- transformers
- Type
- gemma2
- License
- gemma
- Created
- Jul 21, 2024
- Updated
- Jul 21, 2024