Update README.md

README.md

@@ -13,7 +13,7 @@ LoRA weights
 
 This repository features an example of how to utilize the `xllm` library. Included is a solution for a common type of assessment given to LLM engineers, who typically earn between $120,000 to $140,000 annually. The work, which took 6-7 hours to complete, is representative of actual tasks in the field.
 
-[<img src="https://github.com/BobaZooba/xllm/blob/main/static/images/xllm-badge.png" alt="Powered by X—LLM" width="175" height="32"/>](https://github.com/BobaZooba/xllm)
+[<img src="https://cdn-uploads.huggingface.co/production/uploads/6074d5f1134c000d1ae10d42/JudU3rrPP5i87CfwINANO.png" alt="Powered by X—LLM" width="175" height="32"/>](https://github.com/BobaZooba/xllm)
 
 # Task
 
@@ -258,7 +258,7 @@ In the xllm library, there are several important steps: prepare, train, fuse, qu
 
 I only calculated the loss for the json part, didn't calculate it for the description
 
-<img src="https://github.com/BobaZooba/wgpt/blob/main/images/completion_scheme.jpg" alt="Completion scheme"/>
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6074d5f1134c000d1ae10d42/kHeuMnIuTzfqfswD3Lg-8.jpeg)
 
 ### Results of the training
 
@@ -266,7 +266,7 @@ I only calculated the loss for the json part, didn't calculate it for the descri
 - [Fused model](https://huggingface.co/BobaZooba/WGPT)
 - [W&B link](https://api.wandb.ai/links/bobazooba/8v7pqflf)
 
-<img src="https://github.com/BobaZooba/wgpt/blob/main/images/loss_curve.jpg" alt="Loss curve"/>
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6074d5f1134c000d1ae10d42/ILbN27kYCo9QKV2FwG8wL.jpeg)
 
 # Evaluation