PEFT
Safetensors
English
decision-model
system-1
system-one
calibration
tool-use
agents
guardrails
prompt-injection
lora
Instructions to use grounded-ai/agent-decision-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use grounded-ai/agent-decision-3b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("LiquidAI/d1-3B") model = PeftModel.from_pretrained(base_model, "grounded-ai/agent-decision-3b") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Version 2: steps, prompt injection, grounding and multi-turn call/ask/decline; v1 kept at the v1 tag
Verified signature00c3594
-
Describe uses beyond the cascade: hooks, guardrails, trace labelling
Verified signatureb56bcc6 -
agent-decision-3b: LoRA adapter and calibration for LiquidAI/d1-3B
Verified signature5207534 -
initial commit
Verified signature84ae87c