metadata
base_model: google/gemma-4-e2b-it
library_name: peft
tags:
- base_model:adapter:google/gemma-4-e2b-it
- lora
- peft
- classone
- decision-model
LoRA Adapter — classone-gemma4-e2b
PEFT LoRA adapter for devops-thiago/classone-gemma4-e2b, the ClassOne System 1 decision model built on google/gemma-4-e2b-it.
This subfolder holds only the low-rank adapter weights. The Noul / Choice / Score decision heads live in classone_heads.pt at the repository root — load both.
Adapter Configuration
| Setting | Value |
|---|---|
| Base model | google/gemma-4-e2b-it |
| PEFT type | LORA |
| Rank (r) | 16 |
lora_alpha |
32 |
lora_dropout |
0.05 |
| Bias | none |
| Target modules | .*language_model.*(q_proj|o_proj|gate_proj|up_proj|down_proj).* |
| PEFT version | 0.21.0 |
Usage
from peft import PeftModel
from transformers import AutoModel
base = AutoModel.from_pretrained("google/gemma-4-e2b-it")
model = PeftModel.from_pretrained(base, "devops-thiago/classone-gemma4-e2b", subfolder="lora_backbone")
For end-to-end decision inference (packing questions, calibrated outputs), see the model card.
Attribution & Legal
- Base model: google/gemma-4-e2b-it — subject to the Gemma Terms of Use
- Architecture: devops-thiago/class-one — Apache 2.0