From 12ae107986b2bbf853ffca0f45a2edf85a7f4d35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dr=2E=20Artificial=E6=9B=BE=E5=B0=8F=E5=81=A5?=
<875100501@qq.com>
Date: Thu, 25 Jul 2024 16:15:02 +0800
Subject: [PATCH 1/4] Update README.md
Qwen not QWen
---
README.md | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/README.md b/README.md
index 5fd06c985..44543c413 100644
--- a/README.md
+++ b/README.md
@@ -115,10 +115,10 @@ For detailed inference benchmarks in more devices and more settings, please refe
InternLM (7B - 20B)
InternLM2 (7B - 20B)
InternLM2.5 (7B)
- QWen (1.8B - 72B)
- QWen1.5 (0.5B - 110B)
- QWen1.5 - MoE (0.5B - 72B)
- QWen2 (0.5B - 72B)
+ Qwen (1.8B - 72B)
+ Qwen1.5 (0.5B - 110B)
+ Qwen1.5 - MoE (0.5B - 72B)
+ Qwen2 (0.5B - 72B)
Baichuan (7B)
Baichuan2 (7B-13B)
Code Llama (7B - 34B)
@@ -142,7 +142,7 @@ For detailed inference benchmarks in more devices and more settings, please refe
LLaVA(1.5,1.6) (7B-34B)
InternLM-XComposer2 (7B, 4khd-7B)
InternLM-XComposer2.5 (7B)
- QWen-VL (7B)
+ Qwen-VL (7B)
DeepSeek-VL (7B)
InternVL-Chat (v1.1-v1.5)
InternVL2 (1B-40B)
From 3ba4f8c7297b17e5100436413c68933a934f874b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dr=2E=20Artificial=E6=9B=BE=E5=B0=8F=E5=81=A5?=
<875100501@qq.com>
Date: Sat, 27 Jul 2024 11:45:43 +0800
Subject: [PATCH 2/4] Update README_zh-CN.md
---
README_zh-CN.md | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/README_zh-CN.md b/README_zh-CN.md
index e6b02d70f..144b2c970 100644
--- a/README_zh-CN.md
+++ b/README_zh-CN.md
@@ -116,10 +116,10 @@ LMDeploy TurboMind 引擎拥有卓越的推理能力，在各种规模的模型
InternLM (7B - 20B)
InternLM2 (7B - 20B)
InternLM2.5 (7B)
- QWen (1.8B - 72B)
- QWen1.5 (0.5B - 110B)
- QWen1.5 - MoE (0.5B - 72B)
- QWen2 (0.5B - 72B)
+ Qwen (1.8B - 72B)
+ Qwen1.5 (0.5B - 110B)
+ Qwen1.5 - MoE (0.5B - 72B)
+ Qwen2 (0.5B - 72B)
Baichuan (7B)
Baichuan2 (7B-13B)
Code Llama (7B - 34B)
@@ -143,7 +143,7 @@ LMDeploy TurboMind 引擎拥有卓越的推理能力，在各种规模的模型
LLaVA(1.5,1.6) (7B-34B)
InternLM-XComposer2 (7B, 4khd-7B)
InternLM-XComposer2.5 (7B)
- QWen-VL (7B)
+ Qwen-VL (7B)
DeepSeek-VL (7B)
InternVL-Chat (v1.1-v1.5)
InternVL2 (1B-40B)
From 0585c00d1a6cab25c020bbd3fd423979d0976992 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dr=2E=20Artificial=E6=9B=BE=E5=B0=8F=E5=81=A5?=
<875100501@qq.com>
Date: Sat, 27 Jul 2024 12:07:21 +0800
Subject: [PATCH 3/4] Update supported_models.md
---
.../zh_cn/supported_models/supported_models.md | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/docs/zh_cn/supported_models/supported_models.md b/docs/zh_cn/supported_models/supported_models.md
index ab4692fe1..a42a8ddfb 100644
--- a/docs/zh_cn/supported_models/supported_models.md
+++ b/docs/zh_cn/supported_models/supported_models.md
@@ -14,11 +14,11 @@
| InternLM-XComposer | 7B | Yes | Yes | Yes | Yes |
| InternLM-XComposer2 | 7B, 4khd-7B | Yes | Yes | Yes | Yes |
| InternLM-XComposer2.5 | 7B | Yes | Yes | Yes | Yes |
-| QWen | 1.8B - 72B | Yes | Yes | Yes | Yes |
-| QWen1.5 | 1.8B - 110B | Yes | Yes | Yes | Yes |
-| QWen2 | 1.5B - 72B | Yes | Yes | Yes | Yes |
+| Qwen | 1.8B - 72B | Yes | Yes | Yes | Yes |
+| Qwen1.5 | 1.8B - 110B | Yes | Yes | Yes | Yes |
+| Qwen2 | 1.5B - 72B | Yes | Yes | Yes | Yes |
| Mistral | 7B | Yes | Yes | Yes | No |
-| QWen-VL | 7B | Yes | Yes | Yes | Yes |
+| Qwen-VL | 7B | Yes | Yes | Yes | Yes |
| DeepSeek-VL | 7B | Yes | Yes | Yes | Yes |
| Baichuan | 7B | Yes | Yes | Yes | Yes |
| Baichuan2 | 7B | Yes | Yes | Yes | Yes |
@@ -35,7 +35,7 @@
“-” 表示还没有验证。
```{note}
-turbomind 引擎不支持 window attention。所以，对于应用了 window attention，并开启了对应的开关"use_sliding_window"的模型，比如 Mistral、QWen1.5 等，在推理时，请选择 pytorch engine
+turbomind 引擎不支持 window attention。所以，对于应用了 window attention，并开启了对应的开关"use_sliding_window"的模型，比如 Mistral、Qwen1.5 等，在推理时，请选择 pytorch engine
```
### PyTorch 支持的模型
@@ -55,10 +55,10 @@ turbomind 引擎不支持 window attention。所以，对于应用了 window att
| YI | 6B - 34B | Yes | No | No |
| Mistral | 7B | Yes | No | No |
| Mixtral | 8x7B | Yes | No | No |
-| QWen | 1.8B - 72B | Yes | No | No |
-| QWen1.5 | 0.5B - 110B | Yes | No | No |
-| QWen2 | 0.5B - 72B | Yes | No | No |
-| QWen1.5-MoE | A2.7B | Yes | No | No |
+| Qwen | 1.8B - 72B | Yes | No | No |
+| Qwen1.5 | 0.5B - 110B | Yes | No | No |
+| Qwen2 | 0.5B - 72B | Yes | No | No |
+| Qwen1.5-MoE | A2.7B | Yes | No | No |
| DeepSeek-MoE | 16B | Yes | No | No |
| DeepSeek-V2 | 16B, 236B | Yes | No | No |
| Gemma | 2B-7B | Yes | No | No |
From d2633cdda6f140d05b35e0fa8115c91c5fa27a93 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dr=2E=20Artificial=E6=9B=BE=E5=B0=8F=E5=81=A5?=
<875100501@qq.com>
Date: Sat, 27 Jul 2024 12:10:02 +0800
Subject: [PATCH 4/4] Update supported_models.md
---
docs/en/supported_models/supported_models.md | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/docs/en/supported_models/supported_models.md b/docs/en/supported_models/supported_models.md
index c3ff20625..a08a1aa00 100644
--- a/docs/en/supported_models/supported_models.md
+++ b/docs/en/supported_models/supported_models.md
@@ -14,11 +14,11 @@
| InternLM-XComposer | 7B | Yes | Yes | Yes | Yes |
| InternLM-XComposer2 | 7B, 4khd-7B | Yes | Yes | Yes | Yes |
| InternLM-XComposer2.5 | 7B | Yes | Yes | Yes | Yes |
-| QWen | 1.8B - 72B | Yes | Yes | Yes | Yes |
-| QWen1.5 | 1.8B - 110B | Yes | Yes | Yes | Yes |
-| QWen2 | 1.5B - 72B | Yes | Yes | Yes | Yes |
+| Qwen | 1.8B - 72B | Yes | Yes | Yes | Yes |
+| Qwen1.5 | 1.8B - 110B | Yes | Yes | Yes | Yes |
+| Qwen2 | 1.5B - 72B | Yes | Yes | Yes | Yes |
| Mistral | 7B | Yes | Yes | Yes | No |
-| QWen-VL | 7B | Yes | Yes | Yes | Yes |
+| Qwen-VL | 7B | Yes | Yes | Yes | Yes |
| DeepSeek-VL | 7B | Yes | Yes | Yes | Yes |
| Baichuan | 7B | Yes | Yes | Yes | Yes |
| Baichuan2 | 7B | Yes | Yes | Yes | Yes |
@@ -35,7 +35,7 @@
"-" means not verified yet.
```{note}
-The TurboMind engine doesn't support window attention. Therefore, for models that have applied window attention and have the corresponding switch "use_sliding_window" enabled, such as Mistral, QWen1.5 and etc., please choose the PyTorch engine for inference.
+The TurboMind engine doesn't support window attention. Therefore, for models that have applied window attention and have the corresponding switch "use_sliding_window" enabled, such as Mistral, Qwen1.5 and etc., please choose the PyTorch engine for inference.
```
## Models supported by PyTorch
@@ -55,10 +55,10 @@ The TurboMind engine doesn't support window attention. Therefore, for models tha
| YI | 6B - 34B | Yes | No | No |
| Mistral | 7B | Yes | No | No |
| Mixtral | 8x7B | Yes | No | No |
-| QWen | 1.8B - 72B | Yes | No | No |
-| QWen1.5 | 0.5B - 110B | Yes | No | No |
-| QWen1.5-MoE | A2.7B | Yes | No | No |
-| QWen2 | 0.5B - 72B | Yes | No | No |
+| Qwen | 1.8B - 72B | Yes | No | No |
+| Qwen1.5 | 0.5B - 110B | Yes | No | No |
+| Qwen1.5-MoE | A2.7B | Yes | No | No |
+| Qwen2 | 0.5B - 72B | Yes | No | No |
| DeepSeek-MoE | 16B | Yes | No | No |
| DeepSeek-V2 | 16B, 236B | Yes | No | No |
| Gemma | 2B-7B | Yes | No | No |