LLM360
/

K2-V2

@@ -7,20 +7,24 @@ language:
 # **K2-V2**
-📚 [Tech Report](arxiv_url) - 📝 [Code](github_url) - 🏢 [Project Page](self_url)
 K2-V2 is our best fully open source model to date and ranked among the best open weight models of its class. As the latest base model in the LLM360's strongest project family, K2 features a dense architecture with 70 billion parameters.
-<img src="figures/sft-models.pdf" alt="k2-sft-aime"/>
 Beyond standard competencies like knowledge and conversation, K2 provides advanced capabilities, including long context consistency, deep mathematical knowledge, and reasoning behaviors. These serve as foundational building blocks that enable sophisticated downstream use cases, such as solving complex math problems and executing agentic workflows.
-<img src="figures/base-models.pdf" alt="k2-base-gpqa"/>
 ---
-## **Usage**
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer

 # **K2-V2**
+📚 [Tech Report](https://www.llm360.ai/reports/K2_V2_report.pdf ) - 📝 [Code](github_url) - 🏢 [Project Page](https://huggingface.co/LLM360/K2-V2)
+<img src="figures/banner.png" alt="k2-banner-placeholder"/>
+<br>
 K2-V2 is our best fully open source model to date and ranked among the best open weight models of its class. As the latest base model in the LLM360's strongest project family, K2 features a dense architecture with 70 billion parameters.
+<img src="figures/sft-models.png" width="400" alt="k2-sft-aime"/>
 Beyond standard competencies like knowledge and conversation, K2 provides advanced capabilities, including long context consistency, deep mathematical knowledge, and reasoning behaviors. These serve as foundational building blocks that enable sophisticated downstream use cases, such as solving complex math problems and executing agentic workflows.
+<img src="figures/base-models.png" width="400" alt="k2-base-gpqa"/>
 ---
+## **Quick Start**
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer