Update README.md

README.md

@@ -1,13 +1,4 @@
 ---
-tags:
-- merge
-- mergekit
-- lazymergekit
-- M4-ai/tau-0.5B
-- Qwen/Qwen1.5-0.5B
-base_model:
-- M4-ai/tau-0.5B
-- Qwen/Qwen1.5-0.5B
 license: cc-by-sa-4.0
 datasets:
 - Locutusque/UltraTextbooks-2.0
@@ -29,7 +20,7 @@ inference:
 - **Dataset:** UltraTextbooks-2.0
 - **Model Size:** 0.5B parameters
 - **Model Type:** Language Model
-- **Training Procedure:** Further pre-training of Qwen1.5-0.5B on UltraTextbooks-2.0, followed by merging back to the base model using SLERP to prevent catastrophic forgetting. You can access the weights before merging here: https://huggingface.co/M4-ai/tau-0.5B-unmerged
+- **Training Procedure:** Further pre-training of Qwen1.5-0.5B on UltraTextbooks-2.0.
 
 ## Model Use
 tau-0.5B is designed to be a general-purpose language model with enhanced capabilities in the domains of machine learning, mathematics, and coding. It can be used for a wide range of natural language processing tasks, such as: