Text Classification
Transformers
Safetensors
English
qwen3_5_text
text-generation
system-one
system-two
blocks-of-experts
typed-decisions
decision-model
calibrated-probabilities
knowledge-distillation
jev
noul
choice
score
lora
qwen3_5
dual-head
vllm
Eval Results (legacy)
Instructions to use autotrust/JEV-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use autotrust/JEV-27B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="autotrust/JEV-27B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("autotrust/JEV-27B") model = AutoModelForCausalLM.from_pretrained("autotrust/JEV-27B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
3 days ago
-
Model card: AutoTrust/GuruSearch recommendation & search live demo (news.guru.so)
Verified signature14b4252 -
Banner: AutoTrust/GuruSearch recommendation & search live demo
Verified signature2dcbb0d -
Model card: autotrust/JEV recommendation & search live demo (news.guru.so)
Verified signature8e3842f -
Banner: autotrust/JEV recommendation & search live demo
Verified signature8f2286d -
Model card: news search powered by autotrust/JEV (news.guru.so)
Verified signature03fc6dc -
Model card: JEV-powered news search is live (news.guru.so)
Verified signature4469ae4
4 days ago
-
Model card: fix the ModelScope homepage sentence (real-time sync)
Verified signatureff9b67b -
Model card: ModelScope section — links only (no recommendation or install lines)
Verified signature975a3e3 -
Model card: ModelScope section heading without '(China)'
Verified signature10eecb4 -
Model card: ModelScope (China) download links — official AutoTrust-Labs homepage, real-time sync with this repository
Verified signature0f7a4d3
12 days ago
-
serve_decide.py: System 1 only by default for every model (thinking is opt-in)
Verified signature51740a8 -
serve_decide.py: one file for JEV-27B and GEV; optional adaptive thinking (thinking=auto|on, reasoning_effort, think_budget; off by default for JEV-27B), answer read-out that also works with speculative decoding
Verified signaturee6b6a72
13 days ago
-
Model card: "New (1 October 2026)" summary at the top
Verified signature962701f -
System 1 over HTTP (POST /v1/decide, serve_decide.py), choice up to 256 options, prompt guide, 256K context test
Verified signaturec917c6d
14 days ago
-
Update README.md
Verified signature924a8c7
18 days ago
-
Publish JEV-27B model and evaluation results
Co-authored-by: cloudyu <cloudyu@users.noreply.huggingface.co>9b1f6fd