DOC: Update multimodal doc

doc/source/index.rst

@@ -188,11 +188,11 @@ Explore the API
 
       Learn how to generate images with Xinference.
 
-    .. grid-item-card::  Vision
-      :link: vision
+    .. grid-item-card::  Multimodal
+      :link: multimodal
       :link-type: ref
 
-      Learn how to process image with LLMs.
+      Learn how to process images and audio with LLMs.
 
 
 .. grid:: 2

doc/source/locale/zh_CN/LC_MESSAGES/getting_started/installation.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Xinference \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-01-21 14:27+0800\n"
+"POT-Creation-Date: 2025-01-26 11:51+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -144,8 +144,8 @@ msgstr ""
 #: ../../source/getting_started/installation.rst:47
 msgid ""
 "``deepseek``, ``deepseek-coder``, ``deepseek-chat``, ``deepseek-coder-"
-"instruct``, ``deepseek-v2-chat``, ``deepseek-v2-chat-0628``, "
-"``deepseek-v2.5``"
+"instruct``, ``deepseek-r1-distill-qwen``, ``deepseek-v2-chat``, "
+"``deepseek-v2-chat-0628``, ``deepseek-v2.5``"
 msgstr ""
 
 #: ../../source/getting_started/installation.rst:48
@@ -296,25 +296,3 @@ msgstr "其他平台"
 msgid ":ref:`Ascend NPU <installation_npu>`"
 msgstr ""
 
-#~ msgid ""
-#~ "``llama-2``, ``llama-3``, ``llama-3.1``, "
-#~ "``llama-2-chat``, ``llama-3-instruct``, "
-#~ "``llama-3.1-instruct``"
-#~ msgstr ""
-
-#~ msgid "``baichuan``, ``baichuan-chat``, ``baichuan-2-chat``"
-#~ msgstr ""
-
-#~ msgid ""
-#~ "``internlm-16k``, ``internlm-chat-7b``, "
-#~ "``internlm-chat-8k``, ``internlm-chat-20b``"
-#~ msgstr ""
-
-#~ msgid ""
-#~ "``deepseek``, ``deepseek-coder``, ``deepseek-"
-#~ "chat``, ``deepseek-coder-instruct``"
-#~ msgstr ""
-
-#~ msgid "``vicuna-v1.3``, ``vicuna-v1.5``"
-#~ msgstr ""
-

doc/source/locale/zh_CN/LC_MESSAGES/index.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Xinference \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-01-22 14:24+0800\n"
+"POT-Creation-Date: 2025-01-26 11:51+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -120,12 +120,12 @@ msgid "Learn how to generate images with Xinference."
 msgstr "学习如何使用Xinference生成图像。"
 
 #: ../../source/index.rst:191
-msgid "Vision"
-msgstr "视觉"
+msgid "Multimodal"
+msgstr "多模态"
 
 #: ../../source/index.rst:195
-msgid "Learn how to process image with LLMs."
-msgstr "学习如何使用 LLM 处理图像。"
+msgid "Learn how to process images and audio with LLMs."
+msgstr "学习如何使用 LLM 处理图像和音频。"
 
 #: ../../source/index.rst:200
 msgid "Audio"
@@ -182,3 +182,7 @@ msgstr "贡献"
 #: ../../source/index.rst:276
 msgid ":fab:`github` Create a pull request"
 msgstr ":fab:`github` 在 Github 上提 PR"
+
+#~ msgid "Vision"
+#~ msgstr "视觉"
+

doc/source/locale/zh_CN/LC_MESSAGES/models/index.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Xinference \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-08-13 17:44+0800\n"
+"POT-Creation-Date: 2025-01-26 11:51+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -184,12 +184,12 @@ msgid "Learn how to generate images with Xinference."
 msgstr "学习如何使用Xinference生成图像。"
 
 #: ../../source/models/index.rst:202
-msgid "Vision"
-msgstr "视觉"
+msgid "Multimodal"
+msgstr "多模态"
 
 #: ../../source/models/index.rst:206
-msgid "Learn how to process image with LLMs."
-msgstr "学习如何使用 LLM 处理图像。"
+msgid "Learn how to process images and audio with LLMs."
+msgstr "学习如何使用 LLM 处理图像和音频。"
 
 #: ../../source/models/index.rst:211
 msgid "Audio"

doc/source/locale/zh_CN/LC_MESSAGES/models/model_abilities/audio.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Xinference \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-12-12 06:41+0000\n"
+"POT-Creation-Date: 2025-01-22 14:14+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -17,7 +17,7 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"Generated-By: Babel 2.16.0\n"
+"Generated-By: Babel 2.14.0\n"
 
 #: ../../source/models/model_abilities/audio.rst:5
 msgid "Audio (Experimental)"
@@ -152,7 +152,7 @@ msgid "CosyVoice"
 msgstr ""
 
 #: ../../source/models/model_abilities/audio.rst:66
-msgid "FishSpeech-1.4"
+msgid "FishSpeech-1.5"
 msgstr ""
 
 #: ../../source/models/model_abilities/audio.rst:67
@@ -288,15 +288,15 @@ msgstr ""
 
 #: ../../source/models/model_abilities/audio.rst:391
 msgid ""
-"Clone voice, launch model ``FishSpeech-1.4``. Please use `prompt_speech` "
+"Clone voice, launch model ``FishSpeech-1.5``. Please use `prompt_speech` "
 "instead of `reference_audio` and `prompt_text` instead of "
 "`reference_text` to clone voice from the reference audio for the "
 "FishSpeech model. This arguments is aligned to voice cloning of "
 "CosyVoice."
 msgstr ""
-"克隆语音，启动模型 ``FishSpeech-1.4``。请使用 `prompt_speech`而不是 `"
-"reference_audio` 以及 `prompt_text` 而不是 `reference_text` "
-"来为 FishSpeech 模型提供参考音频。这个参数和 CosyVoice 的语音克隆保持一致。"
+"克隆语音，启动模型 ``FishSpeech-1.5``。请使用 `prompt_speech`而不是 `"
+"reference_audio` 以及 `prompt_text` 而不是 `reference_text` 来为 "
+"FishSpeech 模型提供参考音频。这个参数和 CosyVoice 的语音克隆保持一致。"
 
 #: ../../source/models/model_abilities/audio.rst:417
 msgid "SenseVoiceSmall Offline usage"
@@ -334,4 +334,3 @@ msgstr ""
 "然后当用 Web UI 加载 SenseVoiceSmall 时，添加额外选项，key 是 ``vad_model"
 "``，值是之前的下载路径 ``/path/to/fsmn-vad``。用命令行加载时，增加选项 ``"
 "--vad_model /path/to/fsmn-vad``。"
-

doc/source/locale/zh_CN/LC_MESSAGES/models/model_abilities/image.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Xinference \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2024-12-26 18:49+0800\n"
+"POT-Creation-Date: 2025-01-21 14:27+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language: zh_CN\n"
@@ -116,6 +116,7 @@ msgstr ""
 
 #: ../../source/models/model_abilities/image.rst:46
 #: ../../source/models/model_abilities/image.rst:155
+#: ../../source/models/model_abilities/image.rst:184
 msgid "sd3.5-large-turbo"
 msgstr ""
 
@@ -311,7 +312,18 @@ msgstr "支持 GGUF 量化格式"
 msgid "F16, Q2_K, Q3_K_S, Q4_0, Q4_1, Q4_K_S, Q5_0, Q5_1, Q5_K_S, Q6_K, Q8_0"
 msgstr ""
 
-#: ../../source/models/model_abilities/image.rst:187
+#: ../../source/models/model_abilities/image.rst:180
+msgid ""
+"F16, Q3_K_M, Q3_K_S, Q4_0, Q4_1, Q4_K_M, Q4_K_S, Q5_0, Q5_1, Q5_K_M, "
+"Q5_K_S, Q6_K, Q8_0"
+msgstr ""
+
+#: ../../source/models/model_abilities/image.rst:182
+#: ../../source/models/model_abilities/image.rst:184
+msgid "F16, Q4_0, Q4_1, Q5_0, Q5_1, Q8_0"
+msgstr ""
+
+#: ../../source/models/model_abilities/image.rst:189
 msgid ""
 "We stronly recommend to enable additional option ``cpu_offload`` with "
 "value ``True`` for WebUI, or specify ``--cpu_offload True`` for command "
@@ -320,18 +332,17 @@ msgstr ""
 "我们强烈推荐在 WebUI 上开启额外选项 ``cpu_offload`` 并指定为 ``True``，或"
 "对命令行，指定 ``--cpu_offload True``。"
 
-#: ../../source/models/model_abilities/image.rst:190
+#: ../../source/models/model_abilities/image.rst:192
 msgid "Example:"
 msgstr "例如："
 
-#: ../../source/models/model_abilities/image.rst:196
+#: ../../source/models/model_abilities/image.rst:198
 msgid ""
 "With ``Q2_K`` quantization, you only need around 5 GiB GPU memory to run "
 "Flux.1-dev."
-msgstr ""
-"使用 ``Q2_K`` 量化，你只需要大约 5GB 的显存来运行 Flux.1-dev。"
+msgstr "使用 ``Q2_K`` 量化，你只需要大约 5GB 的显存来运行 Flux.1-dev。"
 
-#: ../../source/models/model_abilities/image.rst:198
+#: ../../source/models/model_abilities/image.rst:200
 msgid ""
 "For those models gguf options are not supported internally, or you want "
 "to download gguf files on you own, you can specify additional option "
@@ -342,53 +353,31 @@ msgstr ""
 "Web UI 指定额外选项 ``gguf_model_path`` 或者用命令行指定 ``--gguf_model_"
 "path /path/to/model_quant.gguf`` 。"
 
-#: ../../source/models/model_abilities/image.rst:204
+#: ../../source/models/model_abilities/image.rst:206
 msgid "Image-to-image"
 msgstr "图生图"
 
-#: ../../source/models/model_abilities/image.rst:206
+#: ../../source/models/model_abilities/image.rst:208
 msgid "You can find more examples of Images API in the tutorial notebook:"
 msgstr "你可以在教程笔记本中找到更多 Images API 的示例。"
 
-#: ../../source/models/model_abilities/image.rst:210
+#: ../../source/models/model_abilities/image.rst:212
 msgid "Stable Diffusion ControlNet"
 msgstr ""
 
-#: ../../source/models/model_abilities/image.rst:213
+#: ../../source/models/model_abilities/image.rst:215
 msgid "Learn from a Stable Diffusion ControlNet example"
 msgstr "学习一个 Stable Diffusion 控制网络的示例"
 
-#: ../../source/models/model_abilities/image.rst:216
+#: ../../source/models/model_abilities/image.rst:218
 msgid "OCR"
 msgstr ""
 
-#: ../../source/models/model_abilities/image.rst:218
+#: ../../source/models/model_abilities/image.rst:220
 msgid "The OCR API accepts image bytes and returns the OCR text."
 msgstr "OCR API 接受图像字节并返回 OCR 文本。"
 
-#: ../../source/models/model_abilities/image.rst:220
+#: ../../source/models/model_abilities/image.rst:222
 msgid "We can try OCR API out either via cURL, or Xinference's python client:"
 msgstr "可以通过 cURL 或 Xinference 的 Python 客户端来尝试 OCR API。"
 
-#~ msgid ""
-#~ "If you are trying to run large "
-#~ "image models liek sd3-medium or FLUX.1"
-#~ " series on GPU card that has "
-#~ "less memory than 24GB, you may "
-#~ "encounter OOM when launching or "
-#~ "inference. Try below solutions."
-#~ msgstr ""
-#~ "如果你试图在显存小于24GB的GPU上运行像"
-#~ "sd3-medium或FLUX.1系列这样的大型图像模型"
-#~ "，你在启动或推理过程中可能会遇到显存"
-#~ "溢出（OOM）的问题。尝试以下解决方案。"
-
-#~ msgid "For FLUX.1 series, try to apply quantization."
-#~ msgstr "对于 FLUX.1 系列，尝试应用量化。"
-
-#~ msgid "For sd3-medium, apply quantization to ``text_encoder_3``."
-#~ msgstr "对于 sd3-medium 模型，对 ``text_encoder_3`` 应用量化。"
-
-#~ msgid "Or removing memory-intensive T5-XXL text encoder for sd3-medium."
-#~ msgstr "或者，移除 sd3-medium 模型中内存密集型的 T5-XXL 文本编码器。"
-