Instructions to use ArthurZ/JEV-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArthurZ/JEV-9B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArthurZ/JEV-9B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Decision files next to the model: decision.json, decision_head.json
Browse files- decision.json +15 -0
- decision_head.json +18 -0
decision.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"labels": {},
|
| 3 |
+
"temperature": {
|
| 4 |
+
"noul": 1.0022178236691426,
|
| 5 |
+
"choice": 0.9840233476014968,
|
| 6 |
+
"score": 1.012184473350984
|
| 7 |
+
},
|
| 8 |
+
"calibration": null,
|
| 9 |
+
"noul_band": null,
|
| 10 |
+
"noul_options": [
|
| 11 |
+
"false",
|
| 12 |
+
"true"
|
| 13 |
+
],
|
| 14 |
+
"sort_choices": false
|
| 15 |
+
}
|
decision_head.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"JevDecisionHead"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 4096,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"model_type": "jev",
|
| 9 |
+
"num_verbalizers": 24,
|
| 10 |
+
"offsets": {
|
| 11 |
+
"choice": 8,
|
| 12 |
+
"noul": 0,
|
| 13 |
+
"score": 2
|
| 14 |
+
},
|
| 15 |
+
"softcap": null,
|
| 16 |
+
"transformers_version": "5.19.0.dev0",
|
| 17 |
+
"transformers_weights": "decision_head/model.safetensors"
|
| 18 |
+
}
|