Update README.md: update link to paper on arXiv

README.md

@@ -32,9 +32,9 @@ pipeline_tag: text-generation
 
 An open weights model combining the intelligence of R1 with the token efficiency of V3.
 
-For details on the construction process and analyses of Chimera model variants, please [read our paper](./paper/assembly_of_experts.pdf). 
+For details on the construction process and analyses of Chimera model variants, please [read our paper](https://arxiv.org/abs/2506.14794). 
 
-[Announcement on X](https://x.com/tngtech/status/1916284566127444468) | [LinkedIn post](https://www.linkedin.com/posts/tng-technology-consulting_on-the-weekend-we-released-deepseek-r1t-chimera-activity-7323008947236290560-Cf2m) | [Try it on OpenRouter](https://openrouter.ai/tngtech/deepseek-r1t-chimera:free)
+[Paper on arXiV](https://arxiv.org/abs/2506.14794) | [Announcement on X](https://x.com/tngtech/status/1916284566127444468) | [LinkedIn post](https://www.linkedin.com/posts/tng-technology-consulting_on-the-weekend-we-released-deepseek-r1t-chimera-activity-7323008947236290560-Cf2m) | [Try it on OpenRouter](https://openrouter.ai/tngtech/deepseek-r1t-chimera:free)
 
 
 ## Model Details