DOC: update readme & builtin models

README.md

@@ -34,14 +34,14 @@ potential of cutting-edge AI models.
 - Support speech recognition model: [#929](https://github.com/xorbitsai/inference/pull/929)
 - Metrics support: [#906](https://github.com/xorbitsai/inference/pull/906)
 ### New Models
+- Built-in support for [Qwen2-vl-instruct](https://github.com/QwenLM/Qwen2-VL): [#2205](https://github.com/xorbitsai/inference/pull/2205)
+- Built-in support for [MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B): [#2263](https://github.com/xorbitsai/inference/pull/2263)
 - Built-in support for [CogVideoX](https://github.com/THUDM/CogVideo): [#2049](https://github.com/xorbitsai/inference/pull/2049)
 - Built-in support for [flux.1-schnell & flux.1-dev](https://www.basedlabs.ai/tools/flux1): [#2007](https://github.com/xorbitsai/inference/pull/2007)
 - Built-in support for [MiniCPM-V 2.6](https://github.com/OpenBMB/MiniCPM-V): [#2031](https://github.com/xorbitsai/inference/pull/2031)
 - Built-in support for [Kolors](https://huggingface.co/Kwai-Kolors/Kolors): [#2028](https://github.com/xorbitsai/inference/pull/2028)
 - Built-in support for [SenseVoice](https://github.com/FunAudioLLM/SenseVoice): [#2008](https://github.com/xorbitsai/inference/pull/2008)
 - Built-in support for [Mistral Large 2](https://mistral.ai/news/mistral-large-2407/): [#1944](https://github.com/xorbitsai/inference/pull/1944)
-- Built-in support for [llama3.1](https://ai.meta.com/blog/meta-llama-3-1/): [#1932](https://github.com/xorbitsai/inference/pull/1932)
-- Built-in support for [Mistral Nemo](https://mistral.ai/news/mistral-nemo/): [#1936](https://github.com/xorbitsai/inference/pull/1936)
 ### Integrations
 - [Dify](https://docs.dify.ai/advanced/model-configuration/xinference): an LLMOps platform that enables developers (and even non-developers) to quickly build useful applications based on large language models, ensuring they are visual, operable, and improvable.
 - [FastGPT](https://github.com/labring/FastGPT): a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization.

README_zh_CN.md

@@ -31,14 +31,14 @@ Xorbits Inference（Xinference）是一个性能强大且功能全面的分布
 - 支持语音识别模型: [#929](https://github.com/xorbitsai/inference/pull/929)
 - 增加 Metrics 统计信息: [#906](https://github.com/xorbitsai/inference/pull/906)
 ### 新模型
+- 内置 [Qwen2-vl-instruct](https://github.com/QwenLM/Qwen2-VL): [#2205](https://github.com/xorbitsai/inference/pull/2205)
+- 内置 [MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B): [#2263](https://github.com/xorbitsai/inference/pull/2263)
 - 内置 [CogVideoX](https://github.com/THUDM/CogVideo): [#2049](https://github.com/xorbitsai/inference/pull/2049)
 - 内置 [flux.1-schnell & flux.1-dev](https://www.basedlabs.ai/tools/flux1): [#2007](https://github.com/xorbitsai/inference/pull/2007)
 - 内置 [MiniCPM-V 2.6](https://github.com/OpenBMB/MiniCPM-V): [#2031](https://github.com/xorbitsai/inference/pull/2031)
 - 内置 [Kolors](https://huggingface.co/Kwai-Kolors/Kolors): [#2028](https://github.com/xorbitsai/inference/pull/2028)
 - 内置 [SenseVoice](https://github.com/FunAudioLLM/SenseVoice): [#2008](https://github.com/xorbitsai/inference/pull/2008)
 - 内置 [Mistral Large 2](https://mistral.ai/news/mistral-large-2407/): [#1944](https://github.com/xorbitsai/inference/pull/1944)
-- 内置 [llama3.1](https://ai.meta.com/blog/meta-llama-3-1/): [#1932](https://github.com/xorbitsai/inference/pull/1932)
-- 内置 [Mistral Nemo](https://mistral.ai/news/mistral-nemo/): [#1936](https://github.com/xorbitsai/inference/pull/1936)
 ### 集成
 - [FastGPT](https://doc.fastai.site/docs/development/custom-models/xinference/)：一个基于 LLM 大模型的开源 AI 知识库构建平台。提供了开箱即用的数据处理、模型调用、RAG 检索、可视化 AI 工作流编排等能力，帮助您轻松实现复杂的问答场景。
 - [Dify](https://docs.dify.ai/advanced/model-configuration/xinference): 一个涵盖了大型语言模型开发、部署、维护和优化的 LLMOps 平台。

doc/source/models/builtin/audio/cosyvoice-300m-instruct.rst

@@ -12,7 +12,7 @@ CosyVoice-300M-Instruct
 Specifications
 ^^^^^^^^^^^^^^
 
-- **Model ID:** model-scope/CosyVoice-300M-Instruct
+- **Model ID:** FunAudioLLM/CosyVoice-300M-Instruct
 
 Execute the following command to launch the model::
 

doc/source/models/builtin/audio/cosyvoice-300m-sft.rst

@@ -12,7 +12,7 @@ CosyVoice-300M-SFT
 Specifications
 ^^^^^^^^^^^^^^
 
-- **Model ID:** model-scope/CosyVoice-300M-SFT
+- **Model ID:** FunAudioLLM/CosyVoice-300M-SFT
 
 Execute the following command to launch the model::
 

doc/source/models/builtin/audio/cosyvoice-300m.rst

@@ -12,7 +12,7 @@ CosyVoice-300M
 Specifications
 ^^^^^^^^^^^^^^
 
-- **Model ID:** model-scope/CosyVoice-300M
+- **Model ID:** FunAudioLLM/CosyVoice-300M
 
 Execute the following command to launch the model::
 

doc/source/models/builtin/image/sd3-medium.rst

@@ -6,7 +6,7 @@ sd3-medium
 
 - **Model Name:** sd3-medium
 - **Model Family:** stable_diffusion
-- **Abilities:** text2image, image2image
+- **Abilities:** text2image, image2image, inpainting
 - **Available ControlNet:** None
 
 Specifications

doc/source/models/builtin/llm/index.rst

@@ -46,21 +46,6 @@ The following is a list of built-in LLM in Xinference:
      - 131072
      - C4AI Command-R(+) is a research release of a 35 and 104 billion parameter highly performant generative model.
 
-   * - :ref:`chatglm3 <models_llm_chatglm3>`
-     - chat, tools
-     - 8192
-     - ChatGLM3 is the third generation of ChatGLM, still open-source and trained on Chinese and English data.
-
-   * - :ref:`chatglm3-128k <models_llm_chatglm3-128k>`
-     - chat
-     - 131072
-     - ChatGLM3 is the third generation of ChatGLM, still open-source and trained on Chinese and English data.
-
-   * - :ref:`chatglm3-32k <models_llm_chatglm3-32k>`
-     - chat
-     - 32768
-     - ChatGLM3 is the third generation of ChatGLM, still open-source and trained on Chinese and English data.
-
    * - :ref:`code-llama <models_llm_code-llama>`
      - generate
      - 100000
@@ -171,11 +156,6 @@ The following is a list of built-in LLM in Xinference:
      - 1048576
      - GLM4 is the open source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI.
 
-   * - :ref:`gorilla-openfunctions-v1 <models_llm_gorilla-openfunctions-v1>`
-     - chat
-     - 4096
-     - OpenFunctions is designed to extend Large Language Model (LLM) Chat Completion feature to formulate executable APIs call given natural language instructions and API context.
-
    * - :ref:`gorilla-openfunctions-v2 <models_llm_gorilla-openfunctions-v2>`
      - chat
      - 4096
@@ -276,6 +256,11 @@ The following is a list of built-in LLM in Xinference:
      - 32768
      - MiniCPM-V 2.6 is the latest model in the MiniCPM-V series. The model is built on SigLip-400M and Qwen2-7B with a total of 8B parameters.
 
+   * - :ref:`minicpm3-4b <models_llm_minicpm3-4b>`
+     - chat
+     - 32768
+     - MiniCPM3-4B is the 3rd generation of MiniCPM series. The overall performance of MiniCPM3-4B surpasses Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, being comparable with many recent 7B~9B models.
+
    * - :ref:`mistral-instruct-v0.1 <models_llm_mistral-instruct-v0.1>`
      - chat
      - 8192
@@ -367,7 +352,7 @@ The following is a list of built-in LLM in Xinference:
      - Platypus-70B-instruct is a merge of garage-bAInd/Platypus2-70B and upstage/Llama-2-70b-instruct-v2.
 
    * - :ref:`qwen-chat <models_llm_qwen-chat>`
-     - chat, tools
+     - chat
      - 32768
      - Qwen-chat is a fine-tuned version of the Qwen LLM trained with alignment techniques, specializing in chatting.
 
@@ -396,6 +381,11 @@ The following is a list of built-in LLM in Xinference:
      - 32768
      - Qwen2 is the new series of Qwen large language models. 
 
+   * - :ref:`qwen2-vl-instruct <models_llm_qwen2-vl-instruct>`
+     - chat, vision
+     - 32768
+     - Qwen2-VL: To See the World More Clearly.Qwen2-VL is the latest version of the vision language models in the Qwen model familities.
+
    * - :ref:`seallm_v2 <models_llm_seallm_v2>`
      - generate
      - 8192
@@ -486,16 +476,6 @@ The following is a list of built-in LLM in Xinference:
      - 4096
      - Yi Vision Language (Yi-VL) model is the open-source, multimodal version of the Yi Large Language Model (LLM) series, enabling content comprehension, recognition, and multi-round conversations about images.
 
-   * - :ref:`zephyr-7b-alpha <models_llm_zephyr-7b-alpha>`
-     - chat
-     - 8192
-     - Zephyr-7B-α is the first model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1.
-
-   * - :ref:`zephyr-7b-beta <models_llm_zephyr-7b-beta>`
-     - chat
-     - 8192
-     - Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1
-
 
 .. toctree::
    :maxdepth: 3
@@ -513,12 +493,6 @@ The following is a list of built-in LLM in Xinference:
 
    c4ai-command-r-v01
 
-   chatglm3
-
-   chatglm3-128k
-
-   chatglm3-32k
-
    code-llama
 
    code-llama-instruct
@@ -563,8 +537,6 @@ The following is a list of built-in LLM in Xinference:
 
    glm4-chat-1m
 
-   gorilla-openfunctions-v1
-
    gorilla-openfunctions-v2
 
    gpt-2
@@ -605,6 +577,8 @@ The following is a list of built-in LLM in Xinference:
 
    minicpm-v-2.6
 
+   minicpm3-4b
+
    mistral-instruct-v0.1
 
    mistral-instruct-v0.2
@@ -653,6 +627,8 @@ The following is a list of built-in LLM in Xinference:
 
    qwen2-moe-instruct
 
+   qwen2-vl-instruct
+
    seallm_v2
 
    seallm_v2.5
@@ -689,8 +665,4 @@ The following is a list of built-in LLM in Xinference:
 
    yi-vl-chat
 
-   zephyr-7b-alpha
-
-   zephyr-7b-beta
-