Text Classification
Transformers
Safetensors
English
gemma4
image-text-to-text
system-one
system-two
adaptive-thinking
typed-decisions
decision-model
calibrated-probabilities
jev
noul
choice
score
lora
mixture-of-experts
multimodal
vllm
Eval Results (legacy)
Instructions to use autotrust/GEV-26B-Decide with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use autotrust/GEV-26B-Decide with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="autotrust/GEV-26B-Decide")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("autotrust/GEV-26B-Decide") model = AutoModelForMultimodalLM.from_pretrained("autotrust/GEV-26B-Decide", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download adapter/README.md from autotrust/GEV-26B-Decide: direct link, hf CLI and curl.
- Browser
- Download file 381 Bytes
-
https://huggingface.co/autotrust/GEV-26B-Decide/resolve/main/adapter/README.md
- Command line
-
hf download hf://autotrust/GEV-26B-Decide/adapter/README.md
-
curl -L -o README.md https://huggingface.co/autotrust/GEV-26B-Decide/resolve/main/adapter/README.md
381 Bytes
System 1 adapter (PEFT LoRA)
LoRA adapter for google/gemma-4-26B-A4B-it, part of
autotrust/GEV-26B-Decide. Use it with head.safetensors, judge_config.json
and calibration.json from the repository root; see the model card. adapter_vllm/ is the same System 1 for vLLM.