Update social links

README.md

@@ -70,20 +70,22 @@ Shout out to Brenda Chiang that made the songs.
 
 [Youtube Playthrough](https://www.youtube.com/shorts/rsKrMIF9-rU)
 
+
 ### REQ-04 Social Media Posts
 
-https://www.linkedin.com/posts/pedrolcarvalho_caro5-build-small-hackathon-first-days-activity-7470080151003840512-UbXC
+[Instagram](https://www.instagram.com/pedro.stories/p/DZphpc3E2gJ/)
 
-https://www.linkedin.com/posts/pedrolcarvalho_ai-huggingface-hackaton-activity-7468612916347437056-1WIp
+[Caro5: First Days](https://www.linkedin.com/posts/pedrolcarvalho_caro5-build-small-hackathon-first-days-activity-7470080151003840512-UbXC)
 
-https://www.linkedin.com/posts/pedrolcarvalho_reinforcedlearning-datapipeline-ml-activity-7470506511111200769-BVLh
+[Caro5: Day 3](https://www.linkedin.com/posts/pedrolcarvalho_reinforcedlearning-datapipeline-ml-activity-7470506511111200769-BVLh)
 
-https://www.linkedin.com/posts/pedrolcarvalho_dataset-machinelearning-zobristhashing-activity-7470901078943760386-G0u6
+[Caro5: Day 4](https://www.linkedin.com/posts/pedrolcarvalho_dataset-machinelearning-zobristhashing-activity-7470901078943760386-G0u6)
 
-https://www.linkedin.com/posts/pedrolcarvalho_caro5-day-5-and-6-generating-dataset-and-activity-7471207969880272896-1_r2
+[Caro5: Day 5](https://www.linkedin.com/posts/pedrolcarvalho_caro5-day-5-and-6-generating-dataset-and-activity-7471207969880272896-1_r2)
 
-https://www.linkedin.com/posts/pedrolcarvalho_something-nice-is-coming-soon-activity-7472372419408621568-Cqkh
+[Caro5: Coming soon](https://www.linkedin.com/posts/pedrolcarvalho_something-nice-is-coming-soon-activity-7472372419408621568-Cqkh)
 
+[Caro5: First Release post](https://www.linkedin.com/posts/pedrolcarvalho_machinelearning-gamedev-huggingface-activity-7472656734801637376-EuJ4/)
 
 ### REQ-05: Limited GPU
 
@@ -91,7 +93,7 @@ No GPU needed.
 
 ### REQ-06 Tag your README
 
-Add tagged!
+Tags addewd!
 
 
 ## Sponsors
@@ -188,6 +190,8 @@ The goal is to help players understand *why* a move is good, not just what move
 
 ### Data Generation
 
+Contrary to Gomoku, there wasn't many sources of game datasets, so I started my own. Once the model gets any good, I hope to publish the datasets here. 
+
 Training data was generated through self-play. I started with a basic alpha-beta minimax, put in self-play to generate games. Eventually, I had enough games to start to train a model. It didn't work well as I had no idea how to train a model back then.
 
 But steadily, and with some setbacks, the win rate of the model improved and I could finally deploy it. Since then I have been using this model to generate games and improve it further. The model is now able to play at a very high level, but it is not perfect and there is still room for improvement. It's nowhere near the strongest models out there, from which I mimic their strategies.
@@ -233,6 +237,7 @@ So I had to downscale and choose 2 models to train against smaller models.
 Qwen/Qwen3-1.7B for the funny dragon, and nvidia/OpenReasoning-Nemotron-1.5B for the friendly dragon.
 
 I had fine tuned my first model! [pedroc/caro5-nemotron-15b-friendly-lora-smoke](https://huggingface.co/pedroc/caro5-nemotron-15b-friendly-lora-smoke)
+Then, after more than 1 day running, the second model: [caro5-funny-qwen3-1.7b-run2](https://huggingface.co/build-small-hackathon/caro5-funny-qwen3-1.7b-run2)
 
 Next was doing Quantization on the little model. That reduced the size to less than 1Gb.