Update README.md

README.md

@@ -1,3 +1,64 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+
+## What are G0 / G1 / G1a2 / G1b?
+
+The fields like G0a / G1a / G1a2 in RWKV model names indicate versions of the training data. In terms of data quality, the ranking is:  **G1b > G1a3 > G1a2 > G1a > G1 > G0a2 > G0**.
+
+The RWKV7-G1a model is an advanced version of RWKV7-G1 that was further trained with 1T (1 trillion tokens) of high-quality inference and instruction data. RWKV7-G1a2 was produced by continuing to add more data and training on top of RWKV7-G1a. And so on.
+
+>  [!TIP]
+>  More high-quality data will be added later to form the G1b dataset, and RWKV7-G1b series models will also be trained and open-sourced.
+
+## What is the difference between the RWKV7-G series and the World series?
+
+The RWKV7-G series supports an inference mode, which can be activated using the following format:
+
+```
+User: USER_PROMPT
+
+Assistant: <think
+```
+
+## How to choose the best model?
+
+**Look at the date in the model name** — for the same parameter size, a newer model is better!
+
+For example, for the same 1.5B model, a G1a2 version released on `251005` will definitely be superior to a G1 version released on `250429`.
+
+> [!WARNING] 
+> For the 0.1B and 0.4B models, we recommend using FP16/Q8_0 quantization. Otherwise, the models may fail to complete tasks due to precision loss caused by quantization.
+
+---
+
+
+## G0/G1/G1a2/G1b 是什么?
+
+RWKV 模型名称中的 G0a/G1a/G1a2 等字段是训练数据的版本，数据质量排序：G1b > G1a3 > G1a2 > G1a > G1 > G0a2 > G0 。
+
+RWKV7-G1a 模型是在 RWKV7-G1 模型的基础上继续训练了 1T 优质推理和指令数据的进阶版，RWKV7-G1a2 则是在 RWKV7-G1a 模型的基础上继续添加数据训练，以此类推。
+
+>  [!TIP]
+>  后续会继续添加优质数据形成 G1b 数据集，也会训练并开源 RWKV7-G1b 系列模型。
+
+## RWKV7-G 系列和 World 系列有什么区别？
+
+RWKV7-G 系列模型支持推理模式，可通过以下格式开启推理模式：
+
+```
+User: USER_PROMPT
+
+Assistant: <think
+```
+
+## 如何选择最好的模型？
+
+**看模型名称中的日期**，相同的参数，模型越新越好！
+
+比如同样是 1.5B 模型，发布于 `251005` 的 G1a2 版本必定优于 `250429` 的 G1 版本 。
+
+> [!WARNING] 
+> 对于 0.1B 和 0.4B 模型，我们建议使用 FP16/Q8_0 量化类型。否则模型可能因量化带来的精度损失而无法完成任务。
+
+