Update README.md

README.md

@@ -15,7 +15,7 @@ datasets:
 
 ![Reyna aloobun qwen4B](https://i.imgur.com/QfbOY6c.jpeg)
 - Finetuned [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B), with SFT on variety of CoT tasks including Reasoning, Closed Book Question Answering, Ethics, and more.
-- Datasets : Curated from - [kaist-ai/CoT-Collection](https://huggingface.co/datasets/kaist-ai/CoT-Collection), [euclaise/TinyCoT](https://huggingface.co/datasets/euclaise/TinyCoT) and a very small subset from private data + [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5).
+- Datasets : Curated from - [kaist-ai/CoT-Collection](https://huggingface.co/datasets/kaist-ai/CoT-Collection), [euclaise/TinyCoT](https://huggingface.co/datasets/euclaise/TinyCoT) and a very small subset from [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5).
 - This marks the fourth model in this series. This experiment aims to improve Chain of Thought (CoT) capabilities on smaller language models.
 - In the next run, I may rerun the finetuning experiment using an iterative rationale-bootstrapping procedure inspired by euclaise/Memphis-CoT-3B.
 - Hyperparameter: adamw with eps of 1e-8, cosine decay with 20% warmup, lr=2e-5