RichardErkhov
commited on
Commit
•
bfa3485
1
Parent(s):
df99f85
uploaded readme
Browse files
README.md
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Quantization made by Richard Erkhov.
|
2 |
+
|
3 |
+
[Github](https://github.com/RichardErkhov)
|
4 |
+
|
5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
6 |
+
|
7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
8 |
+
|
9 |
+
|
10 |
+
bigscience-small-testing - bnb 4bits
|
11 |
+
- Model creator: https://huggingface.co/bigscience/
|
12 |
+
- Original model: https://huggingface.co/bigscience/bigscience-small-testing/
|
13 |
+
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
Original model description:
|
18 |
+
---
|
19 |
+
language:
|
20 |
+
- eng
|
21 |
+
tags:
|
22 |
+
- integration
|
23 |
+
pipeline_tag: text-generation
|
24 |
+
---
|
25 |
+
|
26 |
+
# BigScience - testing model
|
27 |
+
|
28 |
+
This model aims to test the conversion between Megatron-LM and transformers. It is a small ```GPT-2```-like model that has been used to debug the script. Use it only for integration tests
|
29 |
+
|