Upload folder using huggingface_hub

Blog.md

@@ -2,7 +2,7 @@
 
 *A Sunday-morning postmortem on teaching a 3B model to do enterprise IT triage with GRPO.*
 
-It's 8 AM on a Sunday. The Meta × PyTorch OpenEnv Hackathon submission is due at 5 PM. My training logs show a loss curve that's been flat at 0.0 for the last thirty minutes.
+It's 1 AM on a Sunday. The Meta × PyTorch OpenEnv Hackathon submission is due at 5 PM. My training logs show a loss curve that's been flat at 0.0 for the last thirty minutes.
 
 A flat loss in supervised learning means convergence. A flat loss in reinforcement learning usually means something else: your model has found a way to game your reward function, and it is now sitting in a local optimum, smug about it.
 

ENV_README.md

@@ -20,11 +20,15 @@ An OpenEnv reinforcement learning environment where an LLM agent resolves enterp
 
 The accompanying training script fine-tunes **Qwen2.5-3B-Instruct → [yahid/triage-agent-qwen3b](https://huggingface.co/yahid/triage-agent-qwen3b)** using GRPO on this environment.
 
+
 ## Links
-- 🤗 **HF Space:** https://huggingface.co/spaces/yahid/triage_agent_env
-- 📓 **Colab Notebook:** [PASTE_LINK]
-- 🧠 **Trained Model:** https://huggingface.co/yahid/triage-agent-qwen3b
-- 📝 **Blog:** [Blog.MD](./Blog.MD)
+
+| | |
+|---|---|
+| 🖥️ **Live Demo** | [yahid/triage_agent_env on HF Spaces](https://huggingface.co/spaces/yahid/triage_agent_env) |
+| 🧠 **Trained Model** | [yahid/triage-agent-qwen3b](https://huggingface.co/yahid/triage-agent-qwen3b) |
+| 📓 **Training Notebook (Colab)** | [Open in Colab](https://colab.research.google.com/drive/1vqkxsp7euJ45cbv4AxfXr5dr-FTOSA3l?usp=sharing) | [Available in this repo](./training/train_grpo_colab_openenvHackathon_finale.ipynb)
+| 📝 **Full Blog Post** | [When my RL agent started writing about Star Wars...](https://huggingface.co/spaces/yahid/triage_agent_env/blob/main/Blog.md) |
 
 ---
 

README.md

@@ -93,7 +93,7 @@ Unanswerable tickets: `escalate=True` earns full primary reward.
 |---|---|
 | 🖥️ **Live Demo** | [yahid/triage_agent_env on HF Spaces](https://huggingface.co/spaces/yahid/triage_agent_env) |
 | 🧠 **Trained Model** | [yahid/triage-agent-qwen3b](https://huggingface.co/yahid/triage-agent-qwen3b) |
-| 📓 **Training Notebook (Colab)** | [Open in Colab](https://colab.research.google.com/drive/1vqkxsp7euJ45cbv4AxfXr5dr-FTOSA3l?usp=sharing) |
+| 📓 **Training Notebook (Colab)** | [Open in Colab](https://colab.research.google.com/drive/1vqkxsp7euJ45cbv4AxfXr5dr-FTOSA3l?usp=sharing) | [Available in this repo](./training/train_grpo_colab_openenvHackathon_finale.ipynb)
 | 📝 **Full Blog Post** | [When my RL agent started writing about Star Wars...](https://huggingface.co/spaces/yahid/triage_agent_env/blob/main/Blog.md) |
 
 ---