@@ -194,6 +194,17 @@ Several folders contain optional materials as a bonus for interested readers:
194194- [ Direct Preference Optimization (DPO) for LLM Alignment] ( ch07/04_preference-tuning-with-dpo/dpo-from-scratch.ipynb )
195195- [ Building a User Interface to Interact With the Instruction Finetuned GPT Model] ( ch07/06_user_interface )
196196
197+ More bonus material from the[ reasoning from scratch] ( https://github.com/rasbt/reasoning-from-scratch ) repository:
198+
199+ - ** Qwen3 (from scratch) basics**
200+ - [ Qwen3 source code walkthrough] ( https://github.com/rasbt/reasoning-from-scratch/blob/main/chC/01_main-chapter-code/chC_main.ipynb )
201+ - [ Optimized Qwen3] ( https://github.com/rasbt/reasoning-from-scratch/tree/main/ch02/03_optimized-LLM )
202+ - ** Evaluation**
203+ - [ Verifier-based evaluation (MATH-500)] ( https://github.com/rasbt/reasoning-from-scratch/tree/main/ch03 )
204+ - [ Multiple-choice evaluation (MMLU)] ( https://github.com/rasbt/reasoning-from-scratch/blob/main/chF/02_mmlu )
205+ - [ LLM leaderboard evaluation] ( https://github.com/rasbt/reasoning-from-scratch/blob/main/chF/03_leaderboards )
206+ - [ LLM-as-a-judge evaluation] ( https://github.com/rasbt/reasoning-from-scratch/blob/main/chF/04_llm-judge )
207+
197208<br >
198209  ;
199210