German
SebastianBodza commited on
Commit
baf88d1
1 Parent(s): a7a4a14

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
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.