docs: upd diagrams, new qwen-qlora-train, qwen35-toolkit links

README.md

@@ -104,7 +104,7 @@ For fine-tuning, use [techwithsergiu/Qwen3.5-text-4B-bnb-4bit](https://huggingfa
 which is the BNB-quantized version of this model.
 
 Training pipeline (QLoRA · Unsloth · TRL):
-[github.com/techwithsergiu/qwen-qlora-train](https://github.com/techwithsergiu/qwen-qlora-train)
+[github.com/techwithsergiu/qwen-qlora-train](https://techwithsergiu.github.io/qwen-qlora-train)
 
 ## Pipeline diagram
 
@@ -112,7 +112,7 @@ Training pipeline (QLoRA · Unsloth · TRL):
 
 ## Conversion
 
-Converted using [qwen35-toolkit](https://github.com/techwithsergiu/qwen35-toolkit) —
+Converted using [qwen35-toolkit](https://techwithsergiu.github.io/qwen35-toolkit) —
 a Python toolkit for BNB quantization, visual tower removal, verification and
 HF Hub publishing of Qwen3.5 models.