Update README.md

README.md

@@ -1,7 +1,7 @@
 ---
 license: mit
 datasets:
-- TIGER-Lab/AceCode-89K
+- TIGER-Lab/AceCode-87K
 language:
 - en
 base_model:
@@ -13,23 +13,23 @@ tags:
 ---
 
 
-# 🂡 AceCode-89K
+# 🂡 AceCode-87K
 
 [Paper](https://arxiv.org/abs/2502.01718) | 
 [Github](https://github.com/TIGER-AI-Lab/AceCoder) |
-[AceCode-89K](https://huggingface.co/datasets/TIGER-Lab/AceCode-89K) |
+[AceCode-87K](https://huggingface.co/datasets/TIGER-Lab/AceCode-87K) |
 [AceCodePair-300K](https://huggingface.co/datasets/TIGER-Lab/AceCodePair-300K) |
 [RM/RL Models](https://huggingface.co/collections/TIGER-Lab/acecoder-67a16011a6c7d65cad529eba)
 
 
-We introduce AceCoder, the first work to propose a fully automated pipeline for synthesizing large-scale reliable tests used for the reward model training and reinforcement learning in the coding scenario. To do this, we curated the dataset AceCode-89K, where we start from a seed code dataset and prompt powerful LLMs to "imagine" proper test cases for the coding question and filter the noisy ones. We sample inferences from existing coder models and compute their pass rate as the reliable and verifiable rewards for both training the reward model and conducting the reinforcement learning for coder LLM.
+We introduce AceCoder, the first work to propose a fully automated pipeline for synthesizing large-scale reliable tests used for the reward model training and reinforcement learning in the coding scenario. To do this, we curated the dataset AceCode-87K, where we start from a seed code dataset and prompt powerful LLMs to "imagine" proper test cases for the coding question and filter the noisy ones. We sample inferences from existing coder models and compute their pass rate as the reliable and verifiable rewards for both training the reward model and conducting the reinforcement learning for coder LLM.
 
 ![https://tiger-ai-lab.github.io/AceCoder/static/images/ac_overview.png](https://tiger-ai-lab.github.io/AceCoder/static/images/ac_overview.png)
 
 
 ## Note
-- **This model official is trained on the hard version of [TIGER-Lab/AceCode-89K](https://huggingface.co/datasets/TIGER-Lab/AceCode-89K) with about 22k examples, using the [TIGER-Lab/AceCodeRM-7B](https://huggingface.co/TIGER-Lab/AceCodeRM-7B) as the reward**
-- You can reproduce the hard version of [TIGER-Lab/AceCode-89K](https://huggingface.co/datasets/TIGER-Lab/AceCode-89K) using [script in our Github](#)
+- **This model official is trained on the hard version of [TIGER-Lab/AceCode-87K](https://huggingface.co/datasets/TIGER-Lab/AceCode-87K) with about 22k examples, using the [TIGER-Lab/AceCodeRM-7B](https://huggingface.co/TIGER-Lab/AceCodeRM-7B) as the reward**
+- You can reproduce the hard version of [TIGER-Lab/AceCode-87K](https://huggingface.co/datasets/TIGER-Lab/AceCode-87K) using [script in our Github](#)
 - The training takes 6 hours to finish on 8 x H100 GPUs in around 80 optimization steps.
 - To reproduce the training, please refer to our [training script in the Github](#)
 - To use the model, please refer to the codes in [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)