From 364322bef9278cc0f5763afd1228bcbb21876687 Mon Sep 17 00:00:00 2001 From: zxy Date: Wed, 9 Jul 2025 10:58:17 +0800 Subject: [PATCH] update reward model docs --- docs/en/supported_models/reward_models.md | 1 + docs/zh_cn/supported_models/reward_models.md | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/en/supported_models/reward_models.md b/docs/en/supported_models/reward_models.md index 6c53e92ff3..68c422a119 100644 --- a/docs/en/supported_models/reward_models.md +++ b/docs/en/supported_models/reward_models.md @@ -6,6 +6,7 @@ LMDeploy supports reward models, which are detailed in the table below: | :--------------: | :-----------: | :------------------------: | | Qwen2.5-Math-RM | 72B | PyTorch | | InternLM2-Reward | 1.8B, 7B, 20B | PyTorch | +| POLAR | 1.8B, 7B | PyTorch | ## Offline Inference diff --git a/docs/zh_cn/supported_models/reward_models.md b/docs/zh_cn/supported_models/reward_models.md index 77f137e65e..b2a727e089 100644 --- a/docs/zh_cn/supported_models/reward_models.md +++ b/docs/zh_cn/supported_models/reward_models.md @@ -6,6 +6,7 @@ LMDeploy 支持以下奖励模型： | :--------------: | :-----------: | :------------------------: | | Qwen2.5-Math-RM | 72B | PyTorch | | InternLM2-Reward | 1.8B, 7B, 20B | PyTorch | +| POLAR | 1.8B, 7B | PyTorch | ## 离线推理