PKU-ML
/

G1-Zero-3B

@@ -16,7 +16,7 @@ library_name: transformers
 ---
-# G1-Zero-7B
 ## Introduction
@@ -30,11 +30,11 @@ G1 brings the following improvements:
 - **NO Compromise on general reasoning**: Crucially, G1 preserves general reasoning ability (GSM8K, MATH, MMLU-Pro), proving its versatility.
-**This repo contains the G1-Zero-7B model**, which has the following features:
 - Type: Causal Language Models
 - Training Stage: RL
 - Architecture: the same with Qwen2.5-Instruct
-- Number of Parameters: 7.62B
 - Context Length: Full 32,768 tokens and generation 8192 tokens
 For more details, please refer to our [paper](https://arxiv.org/pdf/2505.18499) and [GitHub](https://github.com/PKU-ML/G1/tree/main).
@@ -42,7 +42,7 @@ For more details, please refer to our [paper](https://arxiv.org/pdf/2505.18499)
 ## Requirements
-The model is trained based on Qwen/Qwen2.5-7B-Instruct. The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
 With `transformers<4.37.0`, you will encounter the following error:
 ```
@@ -63,7 +63,7 @@ INSTRUCTION_TEMPLATE = """
     Solve the above problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\\boxed{{ANSWER}}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expression that solves the problem. Think step by step before answering.
     """.strip()
-model_name = "PKU-ML/G1-Zero-7B"
 model = AutoModelForCausalLM.from_pretrained(
     model_name,

 ---
+# G1-Zero-3B
 ## Introduction
 - **NO Compromise on general reasoning**: Crucially, G1 preserves general reasoning ability (GSM8K, MATH, MMLU-Pro), proving its versatility.
+**This repo contains the G1-Zero-3B model**, which has the following features:
 - Type: Causal Language Models
 - Training Stage: RL
 - Architecture: the same with Qwen2.5-Instruct
+- Number of Parameters: 3.09B
 - Context Length: Full 32,768 tokens and generation 8192 tokens
 For more details, please refer to our [paper](https://arxiv.org/pdf/2505.18499) and [GitHub](https://github.com/PKU-ML/G1/tree/main).
 ## Requirements
+The model is trained based on Qwen/Qwen2.5-3B-Instruct. The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
 With `transformers<4.37.0`, you will encounter the following error:
 ```
     Solve the above problem efficiently and clearly. The last line of your response should be of the following format: 'Therefore, the final answer is: $\\boxed{{ANSWER}}$. I hope it is correct' (without quotes) where ANSWER is just the final number or expression that solves the problem. Think step by step before answering.
     """.strip()
+model_name = "PKU-ML/G1-Zero-3B"
 model = AutoModelForCausalLM.from_pretrained(
     model_name,