Align the three-round comparator with FinL naming

Model_Card_EN.md

@@ -12,17 +12,21 @@ tags:
 - decision-model
 ---
 
-# Fin-Laya 3-rounds
+# FinL · three-round comparator (native PyTorch)
+
+## Model naming and experiment labels
+
+This is the **FinL three-round comparator**, in native Laya/PyTorch format. The main **FinL** name refers to the [full six-round checkpoint](https://huggingface.co/ya9919/FinL). Its paired earlier MLX format remains [fin-laya-mlx-3-rounds](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds).
 
 ## Project background
 
-S²-MAS is a society-scale multi-agent simulation framework for studying how heterogeneous household decisions become population outcomes under changing conditions. It connects a constructed resource of **500 million household personas**, reusable scenarios, trainable decision models and stateful world updates. Fin-Laya supplies a reusable decision policy: it scores the complete alternatives for a household state and question, allowing the same policy interface to serve different tasks.
+S²-MAS is a society-scale multi-agent simulation framework for studying how heterogeneous household decisions become population outcomes under changing conditions. It connects a constructed resource of **500 million household personas**, reusable scenarios, trainable decision models and stateful world updates. FinL supplies a reusable decision policy: it scores the complete alternatives for a household state and question, allowing the same policy interface to serve different tasks.
 
 The manuscript's paired-condition application evaluates **12 million distinct synthetic household agents and 24 million choices**. A 24-month extension follows 10,000 households through changing income, expenses and bank offers. The applications show how household resources shape consumption responses: persistent income loss draws down reserves and delays purchases, while sustained income gains support both cash reserves and purchases. Repayment feedback affects later offers. These findings connect individual choices to consumption, cash and payment paths over time.
 
 ## Repository role and training
 
-This is the **native Fin-Laya 3-round financial checkpoint**, with approximately 421M parameters, based on Laya's ModernBERT-large encoder and option-scoring head. Two SFT stages followed by native RLCD adapt the model to real-survey data, using **1,721,623 training observations per language**. The [MLX runtime](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds) packages this trained checkpoint for FP16 deployment. The [6-round continuation](https://huggingface.co/ya9919/fin-laya-6-rounds) extends its supervised task coverage.
+This is the **native FinL 3-round financial checkpoint**, with approximately 421M parameters, based on Laya's ModernBERT-large encoder and option-scoring head. Two SFT stages followed by native RLCD adapt the model to real-survey data, using **1,721,623 training observations per language**. The [MLX runtime](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds) packages this trained checkpoint for FP16 deployment. The [6-round continuation](https://huggingface.co/ya9919/FinL) extends its supervised task coverage.
 
 ## Paper results for this checkpoint
 
@@ -37,7 +41,7 @@ On the same shared test, original Laya in native BF16 scores 60.2080% accuracy a
 
 ## Deployment timing
 
-The manuscript's single-request timing uses the [bilingual Fin-Laya checkpoint](https://huggingface.co/ya9919/fin-laya-multilingual-mlx) on one NVIDIA A100 PCIe 40GB in FP16, with batch size and concurrency one and three fixed Chinese cases. Its card and Methods M9 report latency, throughput and the Jev comparison.
+The manuscript's single-request timing uses the [FinL-bilingual checkpoint](https://huggingface.co/ya9919/fin-laya-multilingual-mlx) on one NVIDIA A100 PCIe 40GB in FP16, with batch size and concurrency one and three fixed Chinese cases. Its card and Methods M9 report latency, throughput and the Jev comparison.
 
 ## Model files and inference
 

Model_Card_ZH.md

@@ -12,17 +12,21 @@ tags:
 - decision-model
 ---
 
-# Fin-Laya 3-rounds
+# FinL · three-round comparator (native PyTorch)
+
+## 模型命名与实验标签
+
+本仓库为 **FinL 三轮比较版本**，采用原生 Laya/PyTorch 格式。主要模型 **FinL** 指向[完整六轮 checkpoint](https://huggingface.co/ya9919/FinL)。对应的早期 MLX 格式仍位于 [fin-laya-mlx-3-rounds](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds)。
 
 ## 项目背景
 
-S²-MAS 是面向社会规模的多智能体仿真框架，用于研究异质家庭在条件变化下的决策如何汇总为人口层面的结果。它将**5 亿条构造家庭 persona 资源**、可复用场景、可训练决策模型与持续更新的世界状态连接起来。Fin-Laya 在其中提供可复用的决策策略：根据家庭状态、问题和完整候选选项进行评分，使同一决策接口能够服务不同任务。
+S²-MAS 是面向社会规模的多智能体仿真框架，用于研究异质家庭在条件变化下的决策如何汇总为人口层面的结果。它将**5 亿条构造家庭 persona 资源**、可复用场景、可训练决策模型与持续更新的世界状态连接起来。FinL 在其中提供可复用的决策策略：根据家庭状态、问题和完整候选选项进行评分，使同一决策接口能够服务不同任务。
 
 论文中的配对条件应用实际评估了 **1,200 万个独立合成家庭 agent、共 2,400 万次选择**；24 个月扩展则跟踪 10,000 户家庭在收入、必要支出与银行 offer 变化下的状态。应用结果说明家庭资源如何改变消费响应：持续降收消耗现金储备并推迟购置，持续增收则同时支持现金储备与购置；偿付反馈进一步影响后续 offer，从而将个体选择接到消费、现金与支付的时间路径。
 
 ## 本仓库的模型角色与训练
 
-本仓库提供**原生 Fin-Laya 3-round 金融 checkpoint**，约 421M 参数，采用 Laya 的 ModernBERT-large encoder 与选项评分 head。模型以 real-survey data 为监督，依次经过两次 SFT 和一次原生 RLCD，使用**每语言 1,721,623 条训练观测**。[MLX 运行版本](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds)将同一训练 checkpoint 用于 FP16 部署；[6-round continuation](https://huggingface.co/ya9919/fin-laya-6-rounds)进一步扩展监督任务覆盖。
+本仓库提供**原生 FinL 3-round 金融 checkpoint**，约 421M 参数，采用 Laya 的 ModernBERT-large encoder 与选项评分 head。模型以 real-survey data 为监督，依次经过两次 SFT 和一次原生 RLCD，使用**每语言 1,721,623 条训练观测**。[MLX 运行版本](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds)将同一训练 checkpoint 用于 FP16 部署；[6-round continuation](https://huggingface.co/ya9919/FinL)进一步扩展监督任务覆盖。
 
 ## 本版本的论文结果
 
@@ -37,7 +41,7 @@ Accuracy 对 QA 记录等权计分；question-macro F1 先在每个问题版本
 
 ## 部署速度
 
-论文的单请求速度测量使用[双语 Fin-Laya checkpoint](https://huggingface.co/ya9919/fin-laya-multilingual-mlx)，条件为一张 NVIDIA A100 PCIe 40GB、FP16、batch size 与并发均为 1、三个固定中文案例。对应延迟、吞吐量与 Jev 比较见该版本卡片及 Methods M9。
+论文的单请求速度测量使用[FinL-bilingual checkpoint](https://huggingface.co/ya9919/fin-laya-multilingual-mlx)，条件为一张 NVIDIA A100 PCIe 40GB、FP16、batch size 与并发均为 1、三个固定中文案例。对应延迟、吞吐量与 Jev 比较见该版本卡片及 Methods M9。
 
 ## 模型文件与推理
 

README.md

@@ -12,17 +12,21 @@ tags:
 - decision-model
 ---
 
-# Fin-Laya 3-rounds
+# FinL · three-round comparator (native PyTorch)
+
+## Model naming and experiment labels
+
+This is the **FinL three-round comparator**, in native Laya/PyTorch format. The main **FinL** name refers to the [full six-round checkpoint](https://huggingface.co/ya9919/FinL). Its paired earlier MLX format remains [fin-laya-mlx-3-rounds](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds).
 
 ## Project background
 
-S²-MAS is a society-scale multi-agent simulation framework for studying how heterogeneous household decisions become population outcomes under changing conditions. It connects a constructed resource of **500 million household personas**, reusable scenarios, trainable decision models and stateful world updates. Fin-Laya supplies a reusable decision policy: it scores the complete alternatives for a household state and question, allowing the same policy interface to serve different tasks.
+S²-MAS is a society-scale multi-agent simulation framework for studying how heterogeneous household decisions become population outcomes under changing conditions. It connects a constructed resource of **500 million household personas**, reusable scenarios, trainable decision models and stateful world updates. FinL supplies a reusable decision policy: it scores the complete alternatives for a household state and question, allowing the same policy interface to serve different tasks.
 
 The manuscript's paired-condition application evaluates **12 million distinct synthetic household agents and 24 million choices**. A 24-month extension follows 10,000 households through changing income, expenses and bank offers. The applications show how household resources shape consumption responses: persistent income loss draws down reserves and delays purchases, while sustained income gains support both cash reserves and purchases. Repayment feedback affects later offers. These findings connect individual choices to consumption, cash and payment paths over time.
 
 ## Repository role and training
 
-This is the **native Fin-Laya 3-round financial checkpoint**, with approximately 421M parameters, based on Laya's ModernBERT-large encoder and option-scoring head. Two SFT stages followed by native RLCD adapt the model to real-survey data, using **1,721,623 training observations per language**. The [MLX runtime](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds) packages this trained checkpoint for FP16 deployment. The [6-round continuation](https://huggingface.co/ya9919/fin-laya-6-rounds) extends its supervised task coverage.
+This is the **native FinL 3-round financial checkpoint**, with approximately 421M parameters, based on Laya's ModernBERT-large encoder and option-scoring head. Two SFT stages followed by native RLCD adapt the model to real-survey data, using **1,721,623 training observations per language**. The [MLX runtime](https://huggingface.co/ya9919/fin-laya-mlx-3-rounds) packages this trained checkpoint for FP16 deployment. The [6-round continuation](https://huggingface.co/ya9919/FinL) extends its supervised task coverage.
 
 ## Paper results for this checkpoint
 
@@ -37,7 +41,7 @@ On the same shared test, original Laya in native BF16 scores 60.2080% accuracy a
 
 ## Deployment timing
 
-The manuscript's single-request timing uses the [bilingual Fin-Laya checkpoint](https://huggingface.co/ya9919/fin-laya-multilingual-mlx) on one NVIDIA A100 PCIe 40GB in FP16, with batch size and concurrency one and three fixed Chinese cases. Its card and Methods M9 report latency, throughput and the Jev comparison.
+The manuscript's single-request timing uses the [FinL-bilingual checkpoint](https://huggingface.co/ya9919/fin-laya-multilingual-mlx) on one NVIDIA A100 PCIe 40GB in FP16, with batch size and concurrency one and three fixed Chinese cases. Its card and Methods M9 report latency, throughput and the Jev comparison.
 
 ## Model files and inference