Instructions to use ModalityDance/MRM-PRISM-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModalityDance/MRM-PRISM-V1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ModalityDance/MRM-PRISM-V1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ModalityDance/MRM-PRISM-V1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -59,7 +59,7 @@ python inference.py \
|
|
| 59 |
## Usage Example
|
| 60 |
|
| 61 |
This example shows a typical workflow for a **single user**:
|
| 62 |
-
1) encode text pairs with Skywork-Reward-
|
| 63 |
2) adapt the MRM on the user's few-shot examples (update `shared_weight` only),
|
| 64 |
3) run inference on new pairs for that same user.
|
| 65 |
|
|
|
|
| 59 |
## Usage Example
|
| 60 |
|
| 61 |
This example shows a typical workflow for a **single user**:
|
| 62 |
+
1) encode text pairs with Skywork/Skywork-Reward-Llama-3.1-8B-v0.2 into embeddings,
|
| 63 |
2) adapt the MRM on the user's few-shot examples (update `shared_weight` only),
|
| 64 |
3) run inference on new pairs for that same user.
|
| 65 |
|