Downloads · 30 days
0
aria-devops-llama8b
Arijit-07/aria-devops-llama8b
aria-devops-llama8b is a text generation model from Arijit-07. Use it when you need the model to write or continue text. It is set up for peft.
Trained on the ARIA DevOps Incident Response live RL environment using GRPO.
Access
Public
Updated Apr 26, 2026
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Apr 25, 2026
- Updated
- Apr 26, 2026
- SHA
- e774b099
Try a prompt
Base models
Model card
From the Hugging Face model README
ARIA — DevOps Incident Response Agent
Llama-3.1-8B fine-tuned with GRPO
Trained on the ARIA DevOps Incident Response live RL environment using GRPO.
Training Results
| Task | Baseline | Fine-tuned | Improvement |
|---|---|---|---|
| easy | 0.320 | 0.685 | +0.365 |
| medium | 0.050 | 0.378 | +0.328 |
| hard | 0.190 | 0.869 | +0.679 |
| bonus | 0.152 | 0.682 | +0.530 |
Setup
- Algorithm: GRPO
- Base: Llama-3.1-8B-Instruct
- LoRA rank: 32, alpha: 64
- Episodes: 160 (40 per task)
- GPU: NVIDIA L4, 162 minutes
- Framework: Unsloth + HuggingFace TRL
Links
- Task
- Text Generation
- Library
- peft
- Type
- llama
- Created
- Apr 25, 2026
- Updated
- Apr 26, 2026