Instructions to use callgg/lumina-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use callgg/lumina-decoder with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("callgg/lumina-decoder", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update text_encoder/config.json
Browse files- text_encoder/config.json +1 -1
text_encoder/config.json
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"rms_norm_eps": 1e-06,
|
| 27 |
"rope_theta": 10000.0,
|
| 28 |
"sliding_window": 4096,
|
| 29 |
-
"torch_dtype": "
|
| 30 |
"transformers_version": "4.44.2",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 256000
|
|
|
|
| 26 |
"rms_norm_eps": 1e-06,
|
| 27 |
"rope_theta": 10000.0,
|
| 28 |
"sliding_window": 4096,
|
| 29 |
+
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.44.2",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 256000
|