Update README.md

README.md

@@ -11,10 +11,10 @@ tags:
 ---
 # palmer
 
-palmer-004 a is merge of models targetting to get the performance of palmer-003 all they way to 32k context window. It was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [palmer-002-32k](https://huggingface.co/appvoid/palmer-002-32k) as a base.
+Introducing palmer-004: A Symphony of Innovation in Open-Source AI
 
-palmer-004 performs better than coven_tiny_1.1b_32k_orpo_alpha which is the current sota at open-llm-leaderboard, making this one the best overall 1b model on huggingface as of 06/01/2024.
+We are thrilled to unveil palmer-004, the fourth iteration in our esteemed Palmer series, designed to push the boundaries of performance and context window capacity. Merging the best of palmer-003 with the expansive capabilities of palmer-002-32k, palmer-004 is a testament to the power of innovation and meticulous craftsmanship.
 
-The following models were included in the merge:
-* [coven_tiny_1.1b_32k_orpo_alpha](https://huggingface.co/raidhon/coven_tiny_1.1b_32k_orpo_alpha)
-* [palmer-003](https://huggingface.co/appvoid/palmer-003)
+Crafted using the TIES merge method, palmer-004 elevates its predecessor's prowess to a remarkable 32k context window. This model doesn't just aim to match; it surpasses, outperforming the current state-of-the-art coven_tiny_1.1b_32k_orpo_alpha. As of June 1, 2024, palmer-004 stands as the premier 1B model on Hugging Face, setting a new standard for excellence in the open-source AI community.
+
+Experience the future of language modeling with palmer-004 – a fusion of unparalleled performance and cutting-edge technology, offered to you for free. Join us in this exciting journey of innovation and discovery.