update doc

amumu96 · May 30, 2024 · 0e218c8 · 0e218c8
1 parent c427ccb
commit 0e218c8
Show file tree

Hide file tree

Showing 3 changed files with 76 additions and 8 deletions.
diff --git a/doc/source/models/builtin/llm/index.rst b/doc/source/models/builtin/llm/index.rst
@@ -211,6 +211,11 @@ The following is a list of built-in LLM in Xinference:
      - 204800
      - The second generation of the InternLM model, InternLM2.
 
+   * - :ref:`internvl-chat <models_llm_internvl-chat>`
+     - chat, vision
+     - 32768
+     - InternVL 1.5 is an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. 
+
    * - :ref:`llama-2 <models_llm_llama-2>`
      - generate
      - 4096
@@ -569,6 +574,8 @@ The following is a list of built-in LLM in Xinference:
 
    internlm2-chat
 
+   internvl-chat
+
    llama-2
 
    llama-2-chat

diff --git a/doc/source/models/builtin/llm/internvl-chat.rst b/doc/source/models/builtin/llm/internvl-chat.rst
@@ -0,0 +1,60 @@
+.. _models_llm_internvl-chat:
+
+========================================
+internvl-chat
+========================================
+
+- **Context Length:** 32768
+- **Model Name:** internvl-chat
+- **Languages:** en, zh
+- **Abilities:** chat, vision
+- **Description:** InternVL 1.5 is an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. 
+
+Specifications
+^^^^^^^^^^^^^^
+
+
+Model Spec 1 (pytorch, 2 Billion)
+++++++++++++++++++++++++++++++++++++++++
+
+- **Model Format:** pytorch
+- **Model Size (in billions):** 2
+- **Quantizations:** none
+- **Model ID:** OpenGVLab/Mini-InternVL-Chat-2B-V1-5
+- **Model Hubs**:  `Hugging Face <https://huggingface.co/OpenGVLab/Mini-InternVL-Chat-2B-V1-5>`__
+
+Execute the following command to launch the model, remember to replace ``${quantization}`` with your
+chosen quantization method from the options listed above::
+
+   xinference launch --model-name internvl-chat --size-in-billions 2 --model-format pytorch --quantization ${quantization}
+
+
+Model Spec 2 (pytorch, 26 Billion)
+++++++++++++++++++++++++++++++++++++++++
+
+- **Model Format:** pytorch
+- **Model Size (in billions):** 26
+- **Quantizations:** none
+- **Model ID:** OpenGVLab/InternVL-Chat-V1-5
+- **Model Hubs**:  `Hugging Face <https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5>`__, `ModelScope <https://modelscope.cn/models/AI-ModelScope/InternVL-Chat-V1-5-{quantization}>`__
+
+Execute the following command to launch the model, remember to replace ``${quantization}`` with your
+chosen quantization method from the options listed above::
+
+   xinference launch --model-name internvl-chat --size-in-billions 26 --model-format pytorch --quantization ${quantization}
+
+
+Model Spec 3 (pytorch, 26 Billion)
+++++++++++++++++++++++++++++++++++++++++
+
+- **Model Format:** pytorch
+- **Model Size (in billions):** 26
+- **Quantizations:** Int8
+- **Model ID:** OpenGVLab/InternVL-Chat-V1-5-{quantization}
+- **Model Hubs**:  `Hugging Face <https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5-{quantization}>`__, `ModelScope <https://modelscope.cn/models/AI-ModelScope/InternVL-Chat-V1-5-{quantization}>`__
+
+Execute the following command to launch the model, remember to replace ``${quantization}`` with your
+chosen quantization method from the options listed above::
+
+   xinference launch --model-name internvl-chat --size-in-billions 26 --model-format pytorch --quantization ${quantization}
+
diff --git a/xinference/model/llm/llm_family.json b/xinference/model/llm/llm_family.json
@@ -6009,6 +6009,15 @@
     ],
     "model_description": "InternVL 1.5 is an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. ",
     "model_specs": [
+      {
+            "model_format": "pytorch",
+            "model_size_in_billions": 2,
+            "quantizations": [
+                "none"
+            ],
+            "model_id": "OpenGVLab/Mini-InternVL-Chat-2B-V1-5",
+            "model_revision": "ce3f67acff17281bacbf4b156f402a0580fb9605"
+        },
         {
             "model_format": "pytorch",
             "model_size_in_billions": 26,
@@ -6026,14 +6035,6 @@
             ],
             "model_id": "OpenGVLab/InternVL-Chat-V1-5-{quantization}",
             "model_revision": "acaaed06937c603ab04f084216ecb0268160f538"
-        }, {
-            "model_format": "pytorch",
-            "model_size_in_billions": 2,
-            "quantizations": [
-                "none"
-            ],
-            "model_id": "OpenGVLab/Mini-InternVL-Chat-2B-V1-5",
-            "model_revision": "ce3f67acff17281bacbf4b156f402a0580fb9605"
         }
     ],
     "prompt_style": {