mayank-mishra
commited on
Commit
•
2afcd1b
1
Parent(s):
4a760e2
add mmodel
Browse files
README.md
CHANGED
@@ -1,3 +1,23 @@
|
|
1 |
---
|
2 |
license: openrail
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: openrail
|
3 |
---
|
4 |
+
|
5 |
+
# GPTQ-for-SantaCoder
|
6 |
+
Visit [GPTQ-for-SantaCoder](https://github.com/mayank31398/GPTQ-for-SantaCoder) for instructions on how to use the model weights here.
|
7 |
+
If you want 8-bit weights, visit [santacoder-GPTQ-8bit-128g](https://huggingface.co/mayank31398/santacoder-GPTQ-8bit-128g).
|
8 |
+
|
9 |
+
## Results
|
10 |
+
| [SantaCoder](https://arxiv.org/abs/2301.03988) | Bits | group-size | memory(MiB) | wikitext2 | ptb | c4 | stack | checkpoint size(MB) |
|
11 |
+
| -------------------------------------------------- | ---- | ---------- | ----------- | --------- | ---------- | ---------- | ---------- | ------------------- |
|
12 |
+
| FP32 | 32 | - | 4344.722 | 24.927 | 38.574 | 27.779 | 2.619 | 4394 |
|
13 |
+
| BF16 | 16 | - | 2173.680 | 24.960 | 38.597 | 27.794 | 2.621 | 2195 |
|
14 |
+
| [GPTQ](https://arxiv.org/abs/2210.17323) | 8 | -1 | 1396.548 | 24.936 | 38.592 | 27.785 | 2.619 | 1411 |
|
15 |
+
| [GPTQ](https://arxiv.org/abs/2210.17323) | 4 | -1 | 911.384 | 26.581 | 40.717 | 29.232 | 2.658 | 913 |
|
16 |
+
| [GPTQ](https://arxiv.org/abs/2210.17323) | 3 | -1 | - | 11761.473 | 7273.338 | 9124.941 | 2485.844 | 789 |
|
17 |
+
| [GPTQ](https://arxiv.org/abs/2210.17323) | 2 | -1 | - | 67976.797 | 68994.484 | 73294.438 | 45370.488 | 649 |
|
18 |
+
|
19 |
+
# License
|
20 |
+
The model is licenses under the CodeML Open RAIL-M v0.1 license. You can find the full license [here](https://huggingface.co/spaces/bigcode/license).
|
21 |
+
|
22 |
+
# Acknowledgements
|
23 |
+
Thanks to everyone in BigCode who worked so hard to create these code models.
|
model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7d89f54f6ce941cfd0597282e3aa60d6496dfb118116bc0566364488521d4c
|
3 |
+
size 935374317
|