Update README.md

README.md

@@ -1,21 +1,41 @@
 ---
-base_model: unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit
+base_model: unsloth/Meta-Llama-3.1-8B-Instruct
+library_name: peft
+pipeline_tag: text-generation
 tags:
-- text-generation-inference
-- transformers
+- grpo
+- reinforcement-learning
+- devops
+- incident-response
+- openenv
 - unsloth
-- llama
-license: apache-2.0
-language:
-- en
 ---
 
-# Uploaded finetuned  model
+# ARIA — DevOps Incident Response Agent
+### Llama-3.1-8B fine-tuned with GRPO
 
-- **Developed by:** Arijit-07
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit
+Trained on the [ARIA DevOps Incident Response](https://huggingface.co/spaces/Arijit-07/devops-incident-response) 
+live RL environment using GRPO.
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## Training Results
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+| 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** |
+
+![Training Curve](training_curve_8b.png)
+
+## 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
+- Environment: https://huggingface.co/spaces/Arijit-07/devops-incident-response
+- GitHub: https://github.com/Twilight-13/devops-incident-response