SebastianBodza
commited on
Commit
·
baf88d1
1
Parent(s):
a7a4a14
Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ datasets:
|
|
5 |
language:
|
6 |
- de
|
7 |
---
|
8 |
-
# DElefant:
|
9 |
<img src="https://huggingface.co/SebastianBodza/DElefant-MPT/resolve/main/badge_gerlefant.png" style="max-width:200px">
|
10 |
DElefant is a LLM developed for instruction tuned German interactions. This version is built on top of the MPT-30B model from <a href="https://huggingface.co/mosaicml/mpt-30b">MosaicML</a> with a opus-mt translated and afterwards filtered <a href="https://huggingface.co/datasets/SebastianBodza/Ger_WizardLM_evol_instruct_70k_V0">WizardLM</a> dataset. The evolved dataset led to SOTA english LLMs and we hope by incoperating the translated dataset to a base model we can leverage the capabilities for various tasks in german including Code generation.
|
11 |
Due to limitation in translation, the comments inside of the code blocks remained english, however the Coding was kept in working condition.
|
|
|
5 |
language:
|
6 |
- de
|
7 |
---
|
8 |
+
# DElefant-MPT:
|
9 |
<img src="https://huggingface.co/SebastianBodza/DElefant-MPT/resolve/main/badge_gerlefant.png" style="max-width:200px">
|
10 |
DElefant is a LLM developed for instruction tuned German interactions. This version is built on top of the MPT-30B model from <a href="https://huggingface.co/mosaicml/mpt-30b">MosaicML</a> with a opus-mt translated and afterwards filtered <a href="https://huggingface.co/datasets/SebastianBodza/Ger_WizardLM_evol_instruct_70k_V0">WizardLM</a> dataset. The evolved dataset led to SOTA english LLMs and we hope by incoperating the translated dataset to a base model we can leverage the capabilities for various tasks in german including Code generation.
|
11 |
Due to limitation in translation, the comments inside of the code blocks remained english, however the Coding was kept in working condition.
|