update doc

InternLM · Dec 13, 2024 · e5a5085 · e5a5085
1 parent fdaa601
commit e5a5085
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 0 deletions.
diff --git a/docs/en/multi_modal/llava.md b/docs/en/multi_modal/llava.md
@@ -6,11 +6,18 @@ LMDeploy supports the following llava series of models, which are detailed in th
 | :----------------------------------: | :--: | :------------------------: |
 | llava-hf/Llava-interleave-qwen-7b-hf |  7B  |     TurboMind, PyTorch     |
 |       llava-hf/llava-1.5-7b-hf       |  7B  |     TurboMind, PyTorch     |
+|  llava-hf/llava-v1.6-mistral-7b-hf   |  7B  |          PyTorch           |
+|   llava-hf/llava-v1.6-vicuna-7b-hf   |  7B  |          PyTorch           |
+|   liuhaotian/llava-v1.6-mistral-7b   |  7B  |         TurboMind          |
 |   liuhaotian/llava-v1.6-vicuna-7b    |  7B  |         TurboMind          |
 |   liuhaotian/llava-v1.6-mistral-7b   |  7B  |         TurboMind          |
 
 The next chapter demonstrates how to deploy an Llava model using LMDeploy, with [llava-hf/llava-interleave](https://huggingface.co/llava-hf/llava-interleave-qwen-7b-hf) as an example.
 
+```{note}
+PyTorch engine removes the support of original llava models after v0.6.4. Please use their corresponding transformers models instead, which can be found in https://huggingface.co/llava-hf
+```
+
 ## Installation
 
 Please install LMDeploy by following the [installation guide](../get_started/installation.md).

diff --git a/docs/zh_cn/multi_modal/llava.md b/docs/zh_cn/multi_modal/llava.md
@@ -6,11 +6,17 @@ LMDeploy 支持以下 LLaVA 系列模型，具体如下表所示：
 | :----------------------------------: | :--: | :----------------: |
 | llava-hf/Llava-interleave-qwen-7b-hf |  7B  | TurboMind, PyTorch |
 |       llava-hf/llava-1.5-7b-hf       |  7B  | TurboMind, PyTorch |
+|  llava-hf/llava-v1.6-mistral-7b-hf   |  7B  |      PyTorch       |
+|   llava-hf/llava-v1.6-vicuna-7b-hf   |  7B  |      PyTorch       |
 |   liuhaotian/llava-v1.6-vicuna-7b    |  7B  |     TurboMind      |
 |   liuhaotian/llava-v1.6-mistral-7b   |  7B  |     TurboMind      |
 
 接下来的章节将演示如何使用 LMDeploy 部署 LLaVA 模型，并以 [llava-hf/llava-interleave](https://huggingface.co/llava-hf/llava-interleave-qwen-7b-hf) 为例。
 
+```{note}
+自 0.6.4 之后，PyTorch 引擎移除了对 llava 原始模型的支持。我们建议使用它们对应的 transformers 格式的模型。这些模型可以在 https://huggingface.co/llava-hf 中找到
+```
+
 ## 安装
 
 请按照[安装指南](../get_started/installation.md)安装 LMDeploy。