[docs] fix grpo docs (#4777)

* fix docs

* fix doc

* update readme multi turn link

Author: hjh0119

README.md

@@ -81,7 +81,7 @@ You can contact us and communicate with us by adding our group:
 - 🎁 2025.05.29: Support sequence parallel in pt, sft, dpo and grpo, check script [here](https://github.com/modelscope/ms-swift/tree/main/examples/train/long_text).
 - 🎁 2025.05.11: GRPO now supports custom processing logic for reward models. See the GenRM example [here](./docs/source_en/Instruction/GRPO/DeveloperGuide/reward_model.md).
 - 🎁 2025.04.15: The ms-swift paper has been accepted by AAAI 2025. You can find the paper at [this link](https://ojs.aaai.org/index.php/AAAI/article/view/35383).
-- 🎁 2025.03.23: Multi-round GRPO is now supported for training multi-turn dialogue scenarios (e.g., agent tool calling). Please refer to the [training script](examples/train/grpo/internal/vllm_multi_turn.sh).
+- 🎁 2025.03.23: Multi-round GRPO is now supported for training multi-turn dialogue scenarios (e.g., agent tool calling). Please refer to the [doc](./docs/source_en/Instruction/GRPO/DeveloperGuide/multi_turn.md).
 - 🎁 2025.03.16: Support for Megatron's parallel training techniques is now available. Please see the [Megatron-SWIFT training documentation](https://swift.readthedocs.io/en/latest/Instruction/Megatron-SWIFT-Training.html).
 - 🎁 2025.03.15: Fine-tuning of embedding models for both pure text and multimodal models is supported. Please check the [training script](examples/train/embedding).
 - 🎁 2025.03.05: The hybrid mode for GRPO is supported, with a script for training a 72B model on 4 GPUs (4*80G) available [here](examples/train/grpo/internal/vllm_72b_4gpu.sh). Tensor parallelism with vllm is also supported, with the training script available [here](examples/train/grpo/internal).

README_CN.md

@@ -77,7 +77,7 @@
 - 🎁 2025.05.29: 支持pt、sft、dpo、grpo的序列并行，具体请查看[脚本](https://github.com/modelscope/ms-swift/tree/main/examples/train/long_text)。
 - 🎁 2025.05.11: GRPO中的奖励模型支持自定义处理逻辑，GenRM的例子参考[这里](./docs/source/Instruction/GRPO/DeveloperGuide/奖励模型.md)。
 - 🎁 2025.04.15: ms-swift论文已经被AAAI 2025接收，论文地址在[这里](https://ojs.aaai.org/index.php/AAAI/article/view/35383)。
-- 🎁 2025.03.23: 支持了多轮GRPO，用于构建多轮对话场景的训练(例如agent tool calling)，请查看[训练脚本](examples/train/grpo/internal/vllm_multi_turn.sh)。
+- 🎁 2025.03.23: 支持了多轮GRPO，用于构建多轮对话场景的训练(例如agent tool calling)，请查看[文档](docs/source/Instruction/GRPO/DeveloperGuide/多轮训练.md)。
 - 🎁 2025.03.16: 支持了Megatron的并行技术进行训练，请查看[Megatron-SWIFT训练文档](https://swift.readthedocs.io/zh-cn/latest/Instruction/Megatron-SWIFT训练.html)。
 - 🎁 2025.03.15: 支持纯文本和多模态模型的embedding模型的微调，请查看[训练脚本](examples/train/embedding)。
 - 🎁 2025.03.05: 支持GRPO的hybrid模式，4GPU(4*80G)训练72B模型的脚本参考[这里](examples/train/grpo/internal/vllm_72b_4gpu.sh)。同时支持vllm的tensor并行，训练脚本参考[这里](examples/train/grpo/internal)。

docs/source/Instruction/GRPO/DeveloperGuide/多轮训练.md

@@ -115,7 +115,7 @@ swift rollout \
     --model xxx \
     --use_async_engine true \
     --multi_turn_scheduler xxx \
-    --multi_turns xxx
+    --max_turns xxx
 ```
 
 通过参数`external_plugins`, 我们可以将本地的多轮规划器注册进 ms-swift 中，具体实现参考[代码](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/plugin/plugin.py)

docs/source/Instruction/命令行参数.md

@@ -493,8 +493,8 @@ reward模型参数将在PPO、GRPO中使用。
 - overlong_filter：跳过超长截断的样本，不参与loss计算，默认为False。
 
 cosine 奖励参数
-- cosine_min_len_value_wrong：cosine 奖励函数参数，生成错误答案时，最小长度对应的奖励值。默认值为0.0。
-- cosine_max_len_value_wrong：生成错误答案时，最大长度对应的奖励值。默认值为-0.5。
+- cosine_min_len_value_wrong：cosine 奖励函数参数，生成错误答案时，最小长度对应的奖励值。默认值为-0.5。
+- cosine_max_len_value_wrong：生成错误答案时，最大长度对应的奖励值。默认值为0.0。
 - cosine_min_len_value_correct：生成正确答案时，最小长度对应的奖励值。默认值为1.0。
 - cosine_max_len_value_correct：生成正确答案时，最大长度对应的奖励值。默认值为0.5。
 - cosine_max_len：生成文本的最大长度限制。默认等于 max_completion_length。

docs/source_en/Instruction/Command-line-parameters.md

@@ -511,10 +511,10 @@ The meanings of the following parameters can be referenced [here](https://huggin
 The hyperparameters for the reward function can be found in the [Built-in Reward Functions section](#built-in-reward-functions).
 
 cosine reward function arguments
-- cosine_min_len_value_wrong (default: 0.0): Reward value corresponding to the minimum length when the answer is incorrect. Default is 0.0
-- cosine_max_len_value_wrong (default: -0.5): Reward value corresponding to the maximum length when the answer is incorrect. Default is -0.5
-- cosine_min_len_value_correct (default: 1.0): Reward value corresponding to the minimum length when the answer is correct. Default is 1.0
-- cosine_max_len_value_correct (default: 0.5): Reward value corresponding to the maximum length when the answer is correct. Default is 0.5
+- cosine_min_len_value_wrong (default: -0.5): Reward value corresponding to the minimum length when the answer is incorrect.
+- cosine_max_len_value_wrong (default: 0.0): Reward value corresponding to the maximum length when the answer is incorrect.
+- cosine_min_len_value_correct (default: 1.0): Reward value corresponding to the minimum length when the answer is correct.
+- cosine_max_len_value_correct (default: 0.5): Reward value corresponding to the maximum length when the answer is correct.
 - cosine_max_len (default value equal to the model's maximum generation capacity): Maximum length limit for generated text. Default value equal to max_completion_length
 
 repetition penalty function arguments

docs/source_en/Instruction/GRPO/DeveloperGuide/multi_turn.md

@@ -109,7 +109,7 @@ swift rollout \
     --model xxx \
     --use_async_engine true \
     --multi_turn_scheduler xxx \
-    --multi_turns xxx
+    --max_turns xxx
 ```
 
 Through the `external_plugins` parameter, we can register local multi-round planners into ms-swift. For specific implementation, refer to the [code](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/plugin/plugin.py).