Downloads · 30 days
0
starcoder-GPTQ-4bit-128g
mayank-mishra/starcoder-GPTQ-4bit-128g
starcoder-GPTQ-4bit-128g is a machine learning model from mayank-mishra. 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 bigcode-openrail-m.
Visit GPTQ-for-SantaCoder for instructions on how to use the model weights here. If you want 8-bit weights, visit starcoder-GPTQ-8bit-128g.
Access
Public
Updated May 5, 2023
Repo size
9.3 GB
Likes
16
Public
Repo makeup
Click a slice to open those files.
.pt9.3 GB · 100%
At a glance
- License
- bigcode-openrail-m
- Access
- Public
- Created
- May 5, 2023
- Updated
- May 5, 2023
- SHA
- 982f7f21
Model card
From the Hugging Face model README
GPTQ-for-StarCoder
Visit GPTQ-for-SantaCoder for instructions on how to use the model weights here. If you want 8-bit weights, visit starcoder-GPTQ-8bit-128g.
Results
| StarCoder | Bits | group-size | memory(MiB) | wikitext2 | ptb | c4 | stack | checkpoint size(MB) |
|---|---|---|---|---|---|---|---|---|
| FP32 | 32 | - | 10.801 | 16.425 | 13.402 | 1.738 | 59195 | |
| BF16 | 16 | - | 10.807 | 16.424 | 13.408 | 1.739 | 29597 | |
| GPTQ | 8 | 128 | 10.805 | 15.453 | 13.408 | 1.739 | 16163 | |
| GPTQ | 4 | 128 | 10.989 | 16.839 | 13.676 | 1.757 | 8877 |
License
The model is licenses under the CodeML Open RAIL-M v0.1 license. You can find the full license here.
Acknowledgements
Thanks to everyone in BigCode who worked so hard to create these code models.
- License
- bigcode-openrail-m
- Created
- May 5, 2023
- Updated
- May 5, 2023