Instructions to use codemichaeld/T5Base_fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use codemichaeld/T5Base_fp8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("codemichaeld/T5Base_fp8", 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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
- **Source**: `https://huggingface.co/LifuWang/DistillT5`
|
| 13 |
- **File**: `model.safetensors`
|
| 14 |
- **FP8 Format**: `E5M2`
|
| 15 |
-
- **Correction Mode**:
|
| 16 |
- **Correction File**: `model-correction.safetensors`
|
| 17 |
- **FP8 File**: `model-fp8-e5m2.safetensors`
|
| 18 |
|
|
|
|
| 12 |
- **Source**: `https://huggingface.co/LifuWang/DistillT5`
|
| 13 |
- **File**: `model.safetensors`
|
| 14 |
- **FP8 Format**: `E5M2`
|
| 15 |
+
- **Correction Mode**: per_channel
|
| 16 |
- **Correction File**: `model-correction.safetensors`
|
| 17 |
- **FP8 File**: `model-fp8-e5m2.safetensors`
|
| 18 |
|