From 2131a3c09117e43b1e91606488af47fa48682ab6 Mon Sep 17 00:00:00 2001 From: Cherrytest Date: Sat, 23 Aug 2025 07:42:27 +0000 Subject: [PATCH] Update README.md (#10) - Update README.md (0193a513625b669b8529dc583d213494b0be7b20) Co-authored-by: yong --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index bde8beb..9f2ae14 100644 --- a/README.md +++ b/README.md @@ -474,7 +474,7 @@ Incorporating synthetic instruction data into pretraining leads to improved perf Users can flexibly specify the model's thinking budget. The figure below shows the performance curves across different tasks as the thinking budget varies. For simpler tasks (such as IFEval), the model's chain of thought (CoT) is shorter, and the score exhibits fluctuations as the thinking budget increases. For more challenging tasks (such as AIME and LiveCodeBench), the model's CoT is longer, and the score improves with an increase in the thinking budget. -![thinking_budget](./figures/thinking_budget.png) +![thinking_budget](./thinking_budget.png) Here is an example with a thinking budget set to 512: during the reasoning process, the model periodically triggers self-reflection to estimate the consumed and remaining budget, and delivers the final response once the budget is exhausted or the reasoning concludes. ```