chor‌e: correct URL

README.md

@@ -4,30 +4,26 @@ Meta Llama3 model
 
 ## Variants
 
-
-| No | Variant  |
+| No | Variant |
 | --- | --- |
-| 1 | [8B-onnx](tree/8B-onnx) |
-| 2 | [8B-tensorrtllm-linux-ada](8B-tensorrtllm-linux-ada)  |
-| 3 | [8B-tensorrtllm-windows-ada](tree/8B-tensorrtllm-windows-ada)  |
-| 4 | [8B-gguf](tree/8B-gguf)  |
+| 1 | [8B-onnx](https://huggingface.co/cortexhub/llama3/tree/8B-onnx) |
+| 2 | [8B-tensorrtllm-linux-ada](https://huggingface.co/cortexhub/llama3/tree/8B-tensorrtllm-linux-ada) |
+| 3 | [8B-tensorrtllm-windows-ada](https://huggingface.co/cortexhub/llama3/tree/8B-tensorrtllm-windows-ada) |
+| 4 | [8B-gguf](https://huggingface.co/cortexhub/llama3/tree/8B-gguf) |
 
 ## Use it with Jan (UI)
 
 1. Install Jan using [Quickstart](https://jan.ai/docs/quickstart)
-
 2. Use `cortexhub/llama3` in Jan model Hub
 
-
 ## Use it with Cortex (CLI)
 
-1. Install cortex using [Quick start](https://cortex.jan.ai/docs/quickstart)
-
-2. `cortex run llama3`
+1. Install Cortex using [Quickstart](https://cortex.jan.ai/docs/quickstart)
+2. Run the model with the command: `cortex run llama3`
 
 ## Credits
 
-- Author: meta-llama
-- Converter: [Homebrew](https://www.homebrew.ltd/)
-- Original License: [Licence](https://llama.meta.com/llama3/license/)
-- Papers: 
+- **Author:** meta-llama
+- **Converter:** [Homebrew](https://www.homebrew.ltd/)
+- **Original License:** [Licence](https://llama.meta.com/llama3/license/)
+- **Papers:** N/A