Commit
·
4a6431a
1
Parent(s):
2879674
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,6 @@ pipeline_tag: text-generation
|
|
| 18 |
|
| 19 |
<br>
|
| 20 |
|
| 21 |
-
# The project is currently in progress. Please refrain from using weights and datasets.
|
| 22 |
KORANI is derived from GORANI, a project within llama2 that experiments with the distribution of appropriate datasets to transfer or distill knowledge based on English datasets. Officially, it's called Grid Of Ranvier Node In llama2 (GORANI), based on the biological term Ranvier Node, and aims to explore the optimal dataset for transferring knowledge in various languages and specific domains. Due to strict licensing issues with English datasets, gorani is primarily for research purposes. Therefore, we are refining and training a commercially usable Korean dataset on top of llama2, based on the experimental results of the GORANI project, and this project is named KORANI (Korean GORANI).
|
| 23 |
- We are currently conducting experiments using various techniques such as max sequence length, rope scaling, attention sinks, and flash attention 2.
|
| 24 |
- Please do not use the current model weights as they are not useful.
|
|
|
|
| 18 |
|
| 19 |
<br>
|
| 20 |
|
|
|
|
| 21 |
KORANI is derived from GORANI, a project within llama2 that experiments with the distribution of appropriate datasets to transfer or distill knowledge based on English datasets. Officially, it's called Grid Of Ranvier Node In llama2 (GORANI), based on the biological term Ranvier Node, and aims to explore the optimal dataset for transferring knowledge in various languages and specific domains. Due to strict licensing issues with English datasets, gorani is primarily for research purposes. Therefore, we are refining and training a commercially usable Korean dataset on top of llama2, based on the experimental results of the GORANI project, and this project is named KORANI (Korean GORANI).
|
| 22 |
- We are currently conducting experiments using various techniques such as max sequence length, rope scaling, attention sinks, and flash attention 2.
|
| 23 |
- Please do not use the current model weights as they are not useful.
|