Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# German MoE GPT v8 - OPUS EDITION
|
| 2 |
|
| 3 |
A research-grade language model with state-of-the-art Mixture-of-Experts (MoE) architecture, trained on consumer hardware (RTX 4090). This implementation follows best practices from recent MoE research (ST-MoE, Switch Transformer) while maintaining full cross-platform compatibility.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- de
|
| 4 |
+
license: mit
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- text-generation
|
| 8 |
+
- pytorch
|
| 9 |
+
- causal-lm
|
| 10 |
+
- mixture-of-experts
|
| 11 |
+
- moe
|
| 12 |
+
- german
|
| 13 |
+
- gpt
|
| 14 |
+
- language-model
|
| 15 |
+
base_model: []
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
+
model-index:
|
| 18 |
+
- name: german-moe-gpt-v8-pretrained
|
| 19 |
+
results: []
|
| 20 |
+
datasets:
|
| 21 |
+
- wikipedia
|
| 22 |
+
widget:
|
| 23 |
+
- text: "Die Hauptstadt von Deutschland ist"
|
| 24 |
+
example_title: "German Capital"
|
| 25 |
+
- text: "Künstliche Intelligenz ist"
|
| 26 |
+
example_title: "AI Definition"
|
| 27 |
+
- text: "Es war einmal"
|
| 28 |
+
example_title: "Story Beginning"
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
# German MoE GPT v8 - OPUS EDITION
|
| 32 |
|
| 33 |
A research-grade language model with state-of-the-art Mixture-of-Experts (MoE) architecture, trained on consumer hardware (RTX 4090). This implementation follows best practices from recent MoE research (ST-MoE, Switch Transformer) while maintaining full cross-platform compatibility.
|