Zero-Shot Classification
Transformers
Safetensors
matilda_jev
feature-extraction
matilda
jev
decision-model
classification
maincode
custom_code
Instructions to use Maincode/Matilda-Jev-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maincode/Matilda-Jev-v1.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Maincode/Matilda-Jev-v1.5", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Maincode/Matilda-Jev-v1.5", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ tags:
|
|
| 7 |
- decision-model
|
| 8 |
- classification
|
| 9 |
- maincode
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# MATILDA JEV v1.5 by Maincode
|
|
@@ -104,4 +106,4 @@ peak was 2e-6, repeating the original 1,000-step warmup/cosine cycle. This stage
|
|
| 104 |
used supervised training with replay distillation, not reinforcement learning.
|
| 105 |
|
| 106 |
The source checkpoint and the released weight files were SHA-256 verified.
|
| 107 |
-
The upstream license and runtime notices are retained in this package.
|
|
|
|
| 7 |
- decision-model
|
| 8 |
- classification
|
| 9 |
- maincode
|
| 10 |
+
base_model:
|
| 11 |
+
- Qwen/Qwen3.8-27B
|
| 12 |
---
|
| 13 |
|
| 14 |
# MATILDA JEV v1.5 by Maincode
|
|
|
|
| 106 |
used supervised training with replay distillation, not reinforcement learning.
|
| 107 |
|
| 108 |
The source checkpoint and the released weight files were SHA-256 verified.
|
| 109 |
+
The upstream license and runtime notices are retained in this package.
|