diff --git a/README.md b/README.md index 1354acae0a..d2fc128659 100644 --- a/README.md +++ b/README.md @@ -26,6 +26,7 @@ potential of cutting-edge AI models. ## 🔥 Hot Topics ### Framework Enhancements +- Embedding model support: [#418](https://github.com/xorbitsai/inference/pull/418) - Custom model support: [#325](https://github.com/xorbitsai/inference/pull/325) - LoRA support: [#271](https://github.com/xorbitsai/inference/issues/271) - Multi-GPU support for PyTorch models: [#226](https://github.com/xorbitsai/inference/issues/226) diff --git a/doc/source/models/builtin/bge-base-en.rst b/doc/source/models/builtin/bge-base-en.rst new file mode 100644 index 0000000000..952131eda8 --- /dev/null +++ b/doc/source/models/builtin/bge-base-en.rst @@ -0,0 +1,22 @@ +.. _models_builtin_bge_base_en: + +=========== +bge-base-en +=========== + +- **Model Name:** bge-base-en +- **Languages:** en +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 768 +- **Max Tokens:** 512 +- **Model ID:** BAAI/bge-base-en + +Execute the following command to launch the model:: + + xinference launch --model-name bge-base-en --model-type embedding + + diff --git a/doc/source/models/builtin/bge-base-zh.rst b/doc/source/models/builtin/bge-base-zh.rst new file mode 100644 index 0000000000..5b00cd3879 --- /dev/null +++ b/doc/source/models/builtin/bge-base-zh.rst @@ -0,0 +1,21 @@ +.. _models_builtin_bge_base_zh: + +=========== +bge-base-zh +=========== + +- **Model Name:** bge-base-zh +- **Languages:** zh +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** BAAI/bge-base-zh + +Execute the following command to launch the model:: + + xinference launch --model-name bge-base-zh --model-type embedding + diff --git a/doc/source/models/builtin/bge-large-en.rst b/doc/source/models/builtin/bge-large-en.rst new file mode 100644 index 0000000000..ccb4e58046 --- /dev/null +++ b/doc/source/models/builtin/bge-large-en.rst @@ -0,0 +1,21 @@ +.. _models_builtin_bge_large_en: + +============ +bge-large-en +============ + +- **Model Name:** bge-large-en +- **Languages:** en +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** BAAI/bge-large-en + +Execute the following command to launch the model:: + + xinference launch --model-name bge-large-en --model-type embedding + diff --git a/doc/source/models/builtin/bge-large-zh-noinstruct.rst b/doc/source/models/builtin/bge-large-zh-noinstruct.rst new file mode 100644 index 0000000000..1071d6a0b3 --- /dev/null +++ b/doc/source/models/builtin/bge-large-zh-noinstruct.rst @@ -0,0 +1,21 @@ +.. _models_builtin_bge_large_zh_noinstruct: + +======================= +bge-large-zh-noinstruct +======================= + +- **Model Name:** bge-large-zh-noinstruct +- **Languages:** zh +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** BAAI/bge-large-zh-noinstruct + +Execute the following command to launch the model:: + + xinference launch --model-name bge-large-zh-noinstruct --model-type embedding + diff --git a/doc/source/models/builtin/bge-large-zh.rst b/doc/source/models/builtin/bge-large-zh.rst new file mode 100644 index 0000000000..847a69e508 --- /dev/null +++ b/doc/source/models/builtin/bge-large-zh.rst @@ -0,0 +1,21 @@ +.. _models_builtin_bge_large_zh: + +============ +bge-large-en +============ + +- **Model Name:** bge-large-zh +- **Languages:** zh +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** BAAI/bge-large-zh + +Execute the following command to launch the model:: + + xinference launch --model-name bge-large-zh --model-type embedding + diff --git a/doc/source/models/builtin/bge-small-zh.rst b/doc/source/models/builtin/bge-small-zh.rst new file mode 100644 index 0000000000..489925b6dc --- /dev/null +++ b/doc/source/models/builtin/bge-small-zh.rst @@ -0,0 +1,21 @@ +.. _models_builtin_bge_small_zh: + +============ +bge-large-en +============ + +- **Model Name:** bge_small_zh +- **Languages:** zh +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 512 +- **Max Tokens:** 512 +- **Model ID:** BAAI/bge_small_zh + +Execute the following command to launch the model:: + + xinference launch --model-name bge_small_zh --model-type embedding + diff --git a/doc/source/models/builtin/e5-large-v2.rst b/doc/source/models/builtin/e5-large-v2.rst new file mode 100644 index 0000000000..758e4cbebb --- /dev/null +++ b/doc/source/models/builtin/e5-large-v2.rst @@ -0,0 +1,21 @@ +.. _models_builtin_e5_large_v2: + +========= +gte-large +========= + +- **Model Name:** e5-large-v2 +- **Languages:** en +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** intfloat/e5-large-v2 + +Execute the following command to launch the model:: + + xinference launch --model-name e5-large-v2 --model-type embedding + diff --git a/doc/source/models/builtin/gte-base.rst b/doc/source/models/builtin/gte-base.rst new file mode 100644 index 0000000000..0f379ee13f --- /dev/null +++ b/doc/source/models/builtin/gte-base.rst @@ -0,0 +1,21 @@ +.. _models_builtin_gte_base: + +======== +gte-base +======== + +- **Model Name:** gte-base +- **Languages:** en +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 768 +- **Max Tokens:** 512 +- **Model ID:** thenlper/gte-large + +Execute the following command to launch the model:: + + xinference launch --model-name gte-base --model-type embedding + diff --git a/doc/source/models/builtin/gte-large.rst b/doc/source/models/builtin/gte-large.rst new file mode 100644 index 0000000000..09afa2594c --- /dev/null +++ b/doc/source/models/builtin/gte-large.rst @@ -0,0 +1,21 @@ +.. _models_builtin_gte_large: + +========= +gte-large +========= + +- **Model Name:** gte-large +- **Languages:** en +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** thenlper/gte-large + +Execute the following command to launch the model:: + + xinference launch --model-name gte-large --model-type embedding + diff --git a/doc/source/models/builtin/index.rst b/doc/source/models/builtin/index.rst index a002025037..d454e16446 100644 --- a/doc/source/models/builtin/index.rst +++ b/doc/source/models/builtin/index.rst @@ -86,3 +86,41 @@ Code Assistant Models vicuna-v1.5-16k wizardlm-v1.0 wizardmath-v1.0 + + +Embedding Models +^^^^^^^^^^^^^^^^^^^^^ + +Language: English +++++++++++++++++++++++ +- :ref:`bge-large-en ` +- :ref:`bge-base-en ` +- :ref:`gte-large ` +- :ref:`gte-base ` +- :ref:`e5-large-v2 ` + + +Language: Chinese ++++++++++++++++++++++ +- :ref:`bge-large-zh ` +- :ref:`bge-large-zh-noinstruct ` +- :ref:`bge-base-zh ` +- :ref:`multilingual-e5-large ` +- :ref:`bge-small-zh ` + + + +.. toctree:: + :maxdepth: 2 + :hidden: + + bge-large-en + bge-base-en + gte-large + gte-base + e5-large-v2 + bge-large-zh + bge-large-zh-noinstruct + bge-base-zh + multilingual-e5-large + bge-small-zh diff --git a/doc/source/models/builtin/multilingual-e5-large.rst b/doc/source/models/builtin/multilingual-e5-large.rst new file mode 100644 index 0000000000..44cb618c5e --- /dev/null +++ b/doc/source/models/builtin/multilingual-e5-large.rst @@ -0,0 +1,21 @@ +.. _models_builtin_multilingual_e5_large: + +=========== +bge-base-zh +=========== + +- **Model Name:** multilingual-e5-large +- **Languages:** zh +- **Abilities:** embed + +Specifications +^^^^^^^^^^^^^^ + +- **Dimensions:** 1024 +- **Max Tokens:** 512 +- **Model ID:** intfloat/multilingual-e5-large + +Execute the following command to launch the model:: + + xinference launch --model-name multilingual-e5-large --model-type embedding +