Text Classification
Transformers
Safetensors
English
qwen3_5_moe
image-text-to-text
system-one
typed-decisions
decision-model
calibrated-probabilities
jev
noul
choice
score
mixture-of-experts
vllm
Eval Results (legacy)
Instructions to use lysandre/JEV-35B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lysandre/JEV-35B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="lysandre/JEV-35B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("lysandre/JEV-35B") model = AutoModelForMultimodalLM.from_pretrained("lysandre/JEV-35B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add head.safetensors, judge_config.json (and adapter/) for transformers
Browse files- head.safetensors +3 -0
- judge_config.json +5 -3
head.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8a3127abdf0138ee4baa3b011ad83babfa5a907bc4727dad2cefd726e072672
|
| 3 |
+
size 2163936
|
judge_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"base_model_path": ".",
|
| 3 |
"hidden_size": 2048,
|
| 4 |
"slots": {
|
| 5 |
"num_slots": 264,
|
|
@@ -558,6 +557,10 @@
|
|
| 558 |
"score"
|
| 559 |
],
|
| 560 |
"softcap": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 561 |
"readout": {
|
| 562 |
"type": "last_token",
|
| 563 |
"canvas_len": 1,
|
|
@@ -567,7 +570,6 @@
|
|
| 567 |
},
|
| 568 |
"model_name": "autotrust/JEV-35B",
|
| 569 |
"model_version": "1.1.0",
|
| 570 |
-
"weights_mode": "merged",
|
| 571 |
"base_model": "Qwen/Qwen3.5-35B-A3B",
|
| 572 |
"temperatures": "jev",
|
| 573 |
"system1_merged": {
|
|
@@ -575,4 +577,4 @@
|
|
| 575 |
"decision_head": "264 lm_head rows replaced (bias client-side)",
|
| 576 |
"source_bundle": "autotrust/JEV-35B (adapter + head, merged)"
|
| 577 |
}
|
| 578 |
-
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"hidden_size": 2048,
|
| 3 |
"slots": {
|
| 4 |
"num_slots": 264,
|
|
|
|
| 557 |
"score"
|
| 558 |
],
|
| 559 |
"softcap": null,
|
| 560 |
+
"lm_head_included": true,
|
| 561 |
+
"weights_mode": "merged",
|
| 562 |
+
"adapter_subfolder": null,
|
| 563 |
+
"base_model_path": ".",
|
| 564 |
"readout": {
|
| 565 |
"type": "last_token",
|
| 566 |
"canvas_len": 1,
|
|
|
|
| 570 |
},
|
| 571 |
"model_name": "autotrust/JEV-35B",
|
| 572 |
"model_version": "1.1.0",
|
|
|
|
| 573 |
"base_model": "Qwen/Qwen3.5-35B-A3B",
|
| 574 |
"temperatures": "jev",
|
| 575 |
"system1_merged": {
|
|
|
|
| 577 |
"decision_head": "264 lm_head rows replaced (bias client-side)",
|
| 578 |
"source_bundle": "autotrust/JEV-35B (adapter + head, merged)"
|
| 579 |
}
|
| 580 |
+
}
|