Upload README.md with huggingface_hub

README.md

@@ -5,7 +5,7 @@ license: mit
 
 ## Overview
 
-The 'test-deepseek-R1-Distill-Qwen-1.5B' model is an advanced machine learning architecture designed for natural language processing tasks, specifically fine-tuned for improved efficiency and performance. This model leverages the distilled version of the Qwen 1.5B architecture, enabling faster inference times while maintaining a high level of accuracy in understanding and generating human-like text. Its primary use cases include conversational agents, content generation, and semantic search, making it a versatile tool for developers and researchers alike. With a focus on streamlined processing and response quality, it excels in applications requiring real-time interaction and dynamic content creation. Users can expect robust performance on various benchmarks, showcasing its ability to handle complex language tasks effectively.
+The 'test-deepseek-R1-Distill-Qwen-1.5B' model is a refined version of the DeepSeek framework, designed for efficient natural language processing tasks. It specializes in distillation methods that enhance the performance of large language models while reducing their computational demands. This model is particularly useful for applications such as text generation, summarization, and conversational AI, making it suitable for both research and practical implementations. Users can expect improved accuracy and faster inference times compared to its predecessors, which allows for greater scalability in real-world scenarios. Overall, the 'test-deepseek-R1-Distill-Qwen-1.5B' represents a significant advancement in the deployment of deep learning solutions for language understanding and generation tasks.
 
 ## Variants
 
@@ -18,12 +18,16 @@ The 'test-deepseek-R1-Distill-Qwen-1.5B' model is an advanced machine learning a
 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
 2. Use in Jan model Hub:
     
+    cortexso/deepseek-r1-distill-qwen-1.5b
+    
 
 ## Use it with Cortex (CLI)
 
 1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
 2. Run the model with command:
     
+    cortex run deepseek-r1-distill-qwen-1.5b
+    
 
 ## Credits