Type: LoRA adapter (PEFT) for Qwen/Qwen2.5-3B-Instruct
Task: incident-response orchestration in a multi-agent OpenEnv environment
Training: TRL GRPOTrainer + Unsloth (real run; curves/logs in the project repo)

Where it comes from (source of truth)

GitHub project: https://github.com/COolAlien35/AIC
Judge env Space: https://huggingface.co/spaces/KINGKK007/aic-training
Results dashboard: https://huggingface.co/spaces/KINGKK007/aic-results-dashboard

How to use (load adapter)

python

# pip install -U transformers peft torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_id = "Qwen/Qwen2.5-3B-Instruct"
adapter_id = "COolAlien35/aic-grpo-adapter-14"

tok = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(base, adapter_id)

# now use `model.generate(...)` normally

COolAlien35/aic-grpo-adapter-l4

AIC GRPO LoRA Adapter (Qwen2.5-3B-Instruct)

What this is

Where it comes from (source of truth)

How to use (load adapter)

COolAlien35/
aic-grpo-adapter-l4