[Docs] Align supported models, remove SUPPORTED_MODELS.md (#2435)

yatarkan · web-flow · commit e28202a9999e · 2025-07-16T10:46:13.000Z
Ticket: CVS-169351 Preview: https://yatarkan.github.io/openvino.genai/docs/supported-models/
diff --git a/README.md b/README.md
@@ -524,7 +524,7 @@ int main(int argc, char* argv[]) {
 
 ## Additional materials
 
-- [List of supported models](https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md) (NOTE: models can work, but were not tried yet)
+- [List of supported models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/)
 - [OpenVINO Generative AI workflow](https://docs.openvino.ai/2025/openvino-workflow-generative.html)
 - [Optimum-intel and OpenVINO](https://huggingface.co/docs/optimum/intel/openvino/export)
 
diff --git a/SUPPORTED_MODELS.md b/SUPPORTED_MODELS.md
diff --git a/samples/cpp/rag/README.md b/samples/cpp/rag/README.md
@@ -19,7 +19,7 @@ Follow [Get Started with Samples](https://docs.openvino.ai/2025/get-started/lear
 
 `text_embeddings BAAI/bge-small-en-v1.5 "Document 1" "Document 2"`
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#text-embeddings-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#text-embeddings-models) for more details.
 
 # Text Embedding Pipeline Usage
 
diff --git a/samples/cpp/speech_generation/README.md b/samples/cpp/speech_generation/README.md
@@ -45,7 +45,7 @@ to run the sample.
 
 It generates `output_audio.wav` file containing the phrase `Hello OpenVINO GenAI` spoken in the target voice.
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#speech-generation-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#speech-generation-models) for more details.
 
 # Text-to-speech pipeline usage
 
diff --git a/samples/cpp/text_generation/README.md b/samples/cpp/text_generation/README.md
@@ -30,7 +30,7 @@ Follow [build instruction](../../../src/docs/BUILD.md) to build GenAI samples
 
 GPUs usually provide better performance compared to CPUs. Modify the source code to change the device for inference to the GPU.
 
-See https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/) for more details.
 
 Install [../../deployment-requirements.txt](../../deployment-requirements.txt) to run samples
 ```sh
diff --git a/samples/cpp/visual_language_chat/README.md b/samples/cpp/visual_language_chat/README.md
@@ -29,7 +29,7 @@ Follow [Get Started with Samples](https://docs.openvino.ai/2025/get-started/lear
 
 Discrete GPUs (dGPUs) usually provide better performance compared to CPUs. It is recommended to run larger models on a dGPU with 32GB+ RAM. For example, the model `llava-hf/llava-v1.6-mistral-7b-hf` can benefit from being run on a dGPU. Modify the source code to change the device for inference to the `GPU`.
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#visual-language-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#visual-language-models-vlms) for more details.
 
 ## Run benchmark:
 
diff --git a/samples/cpp/whisper_speech_recognition/README.md b/samples/cpp/whisper_speech_recognition/README.md
@@ -31,7 +31,7 @@ Output:
 timestamps: [0, 2] text:  How are you doing today?
 ```
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#whisper-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#speech-recognition-models-whisper-based) for more details.
 
 # Whisper pipeline usage
 
diff --git a/samples/js/rag/README.md b/samples/js/rag/README.md
@@ -20,7 +20,7 @@ Compile GenAI JavaScript bindings archive first using [the instructions](../../.
 
 Run `npm install` and the example will be ready to run.
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#text-embeddings-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#text-embeddings-models) for more details.
 
 ### Text embedding (`text_embeddings`)
 - **Description:** This is basic text embedding using a causal embedding model.
diff --git a/samples/python/rag/README.md b/samples/python/rag/README.md
@@ -40,7 +40,7 @@ Install [deployment-requirements.txt](../../deployment-requirements.txt) via `pi
 
 `python text_embeddings.py BAAI/bge-small-en-v1.5 "Document 1" "Document 2"`
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#text-embeddings-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#text-embeddings-models) for more details.
 
 # Text Embedding Pipeline Usage
 
diff --git a/samples/python/speech_generation/README.md b/samples/python/speech_generation/README.md
@@ -65,7 +65,7 @@ via `pip install -r ../../deployment-requirements.txt` and then, run a sample:
 
 It generates `output_audio.wav` file containing the phrase `Hello OpenVINO GenAI` spoken in the target voice.
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#speech-generation-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#speech-generation-models) for more details.
 
 # Text-to-speech pipeline usage
 
diff --git a/samples/python/text_generation/README.md b/samples/python/text_generation/README.md
@@ -55,7 +55,7 @@ Follow [build instruction](../../../src/docs/BUILD.md) to build GenAI samples
 
 GPUs usually provide better performance compared to CPUs. Modify the source code to change the device for inference to the GPU.
 
-See https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#large-language-models-llms) for more details.
 
 Install [../../deployment-requirements.txt](../../deployment-requirements.txt) to run samples
 ```sh
diff --git a/samples/python/whisper_speech_recognition/README.md b/samples/python/whisper_speech_recognition/README.md
@@ -59,7 +59,7 @@ Output:
 timestamps: [0, 2] text:  How are you doing today?
 ```
 
-See [SUPPORTED_MODELS.md](../../../SUPPORTED_MODELS.md#whisper-models) for the list of supported models.
+Refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/#speech-recognition-models-whisper-based) for more details.
 
 # Whisper pipeline usage
 
diff --git a/site/docs/supported-models/_components/llm-models-table/models.ts b/site/docs/supported-models/_components/llm-models-table/models.ts
@@ -493,6 +493,7 @@ export const LLM_MODELS: LLMModelType[] = [
           'https://huggingface.co/meta-llama/Llama-2-7b-hf',
           'https://huggingface.co/meta-llama/Llama-2-70b-chat-hf',
           'https://huggingface.co/meta-llama/Llama-2-70b-hf',
+          'https://huggingface.co/microsoft/Llama2-7b-WhoIsHarryPotter',
         ],
       },
       {
@@ -681,21 +682,19 @@ export const LLM_MODELS: LLMModelType[] = [
           'https://huggingface.co/microsoft/Phi-3.5-mini-instruct',
           'https://huggingface.co/microsoft/Phi-4-mini-instruct',
           'https://huggingface.co/microsoft/phi-4',
-          'https://huggingface.co/microsoft/Phi-4-reasoning'
+          'https://huggingface.co/microsoft/Phi-4-reasoning',
         ],
       },
     ],
   },
   {
-    architecture: "PhimoeForCausalLM",
+    architecture: 'PhimoeForCausalLM',
     models: [
       {
-        name: "Phi-3.5-MoE",
-        links: [
-          "https://huggingface.co/microsoft/Phi-3.5-MoE-instruct"
-        ]
-      }
-    ]
+        name: 'Phi-3.5-MoE',
+        links: ['https://huggingface.co/microsoft/Phi-3.5-MoE-instruct'],
+      },
+    ],
   },
   {
     architecture: 'QWenLMHeadModel',
@@ -742,6 +741,7 @@ export const LLM_MODELS: LLMModelType[] = [
           'https://huggingface.co/Qwen/Qwen1.5-7B-Chat',
           'https://huggingface.co/Qwen/Qwen1.5-14B-Chat',
           'https://huggingface.co/Qwen/Qwen1.5-32B-Chat',
+          'https://huggingface.co/Qwen/Qwen1.5-7B-Chat-GPTQ-Int4',
           'https://huggingface.co/Qwen/QwQ-32B',
           'https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B',
           'https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B',
@@ -766,37 +766,37 @@ export const LLM_MODELS: LLMModelType[] = [
     ],
   },
   {
-   architecture: 'Qwen3ForCausalLM',
-   models: [
-    {
-      name: 'Qwen3',
-      links: [
-        'https://huggingface.co/Qwen/Qwen3-0.6B',
-        'https://huggingface.co/Qwen/Qwen3-1.7B',
-        'https://huggingface.co/Qwen/Qwen3-4B',
-        'https://huggingface.co/Qwen/Qwen3-8B',
-        'https://huggingface.co/Qwen/Qwen3-14B',
-        'https://huggingface.co/Qwen/Qwen3-32B',
-        'https://huggingface.co/Qwen/Qwen3-0.6B-Base',
-        'https://huggingface.co/Qwen/Qwen3-1.7B-Base',
-        'https://huggingface.co/Qwen/Qwen3-4B-Base',
-        'https://huggingface.co/Qwen/Qwen3-8B-Base',
-        'https://huggingface.co/Qwen/Qwen3-14B-Base',
-      ]
-    }
-   ]
+    architecture: 'Qwen3ForCausalLM',
+    models: [
+      {
+        name: 'Qwen3',
+        links: [
+          'https://huggingface.co/Qwen/Qwen3-0.6B',
+          'https://huggingface.co/Qwen/Qwen3-1.7B',
+          'https://huggingface.co/Qwen/Qwen3-4B',
+          'https://huggingface.co/Qwen/Qwen3-8B',
+          'https://huggingface.co/Qwen/Qwen3-14B',
+          'https://huggingface.co/Qwen/Qwen3-32B',
+          'https://huggingface.co/Qwen/Qwen3-0.6B-Base',
+          'https://huggingface.co/Qwen/Qwen3-1.7B-Base',
+          'https://huggingface.co/Qwen/Qwen3-4B-Base',
+          'https://huggingface.co/Qwen/Qwen3-8B-Base',
+          'https://huggingface.co/Qwen/Qwen3-14B-Base',
+        ],
+      },
+    ],
   },
   {
     architecture: 'Qwen3MoeForCausalLM',
     models: [
       {
-      name: 'Qwen3MoE',
-      links: [
-        'https://huggingface.co/Qwen/Qwen3-30B-A3B',
-        'https://huggingface.co/Qwen/Qwen3-30B-A3B-Base',
-      ]
-    }
-  ]
+        name: 'Qwen3MoE',
+        links: [
+          'https://huggingface.co/Qwen/Qwen3-30B-A3B',
+          'https://huggingface.co/Qwen/Qwen3-30B-A3B-Base',
+        ],
+      },
+    ],
   },
   {
     architecture: 'StableLmForCausalLM',
diff --git a/site/docs/supported-models/_components/speech-generation-models-table/index.tsx b/site/docs/supported-models/_components/speech-generation-models-table/index.tsx
@@ -0,0 +1,29 @@
+import React from 'react';
+import { BaseModelsTable, LinksCell, StatusCell } from '../base-models-table';
+import { SPEECH_GENERATION_MODELS } from './models';
+
+export default function SpeechGenerationModelsTable(): React.JSX.Element {
+  const headers = ['Architecture', 'Models', 'LoRA Support', 'Example HuggingFace Models'];
+
+  const rows = SPEECH_GENERATION_MODELS.map(({ architecture, models }) => (
+    <>
+      <tr key={architecture}>
+        <td rowSpan={models.length}>
+          <code>{architecture}</code>
+        </td>
+        <td>{models[0].name}</td>
+        <StatusCell value={models[0].loraSupport} />
+        <LinksCell links={models[0].links} />
+      </tr>
+      {models.slice(1).map(({ name, loraSupport, links }) => (
+        <tr key={name}>
+          <td>{name}</td>
+          <StatusCell value={loraSupport} />
+          <LinksCell links={links} />
+        </tr>
+      ))}
+    </>
+  ));
+
+  return <BaseModelsTable headers={headers} rows={rows} />;
+}
diff --git a/site/docs/supported-models/_components/speech-generation-models-table/models.ts b/site/docs/supported-models/_components/speech-generation-models-table/models.ts
@@ -0,0 +1,21 @@
+type SpeechGenerationModelType = {
+  architecture: string;
+  models: Array<{
+    name: string;
+    loraSupport: boolean;
+    links: string[];
+  }>;
+};
+
+export const SPEECH_GENERATION_MODELS: SpeechGenerationModelType[] = [
+  {
+    architecture: 'SpeechT5ForTextToSpeech',
+    models: [
+      {
+        name: 'SpeechT5 TTS',
+        loraSupport: false,
+        links: ['https://huggingface.co/microsoft/speecht5_tts'],
+      },
+    ],
+  },
+];
diff --git a/site/docs/supported-models/_components/text-embeddings-models-table/index.tsx b/site/docs/supported-models/_components/text-embeddings-models-table/index.tsx
@@ -0,0 +1,19 @@
+import React from 'react';
+import { BaseModelsTable, LinksCell, StatusCell } from '../base-models-table';
+import { TEXT_EMBEDDINGS_MODELS } from './models';
+
+export default function TextEmbeddingsModelsTable(): React.JSX.Element {
+  const headers = ['Architecture', 'LoRA Support', 'Example HuggingFace Models'];
+
+  const rows = TEXT_EMBEDDINGS_MODELS.map(({ architecture, models }) => (
+    <tr key={architecture}>
+      <td>
+        <code>{architecture}</code>
+      </td>
+      <StatusCell value={models[0].loraSupport} />
+      <LinksCell links={models[0].links} />
+    </tr>
+  ));
+
+  return <BaseModelsTable headers={headers} rows={rows} />;
+}
diff --git a/site/docs/supported-models/_components/text-embeddings-models-table/models.ts b/site/docs/supported-models/_components/text-embeddings-models-table/models.ts
@@ -0,0 +1,61 @@
+type TextEmbeddingsModelType = {
+  architecture: string;
+  models: Array<{
+    loraSupport: boolean;
+    links: string[];
+  }>;
+};
+
+export const TEXT_EMBEDDINGS_MODELS: TextEmbeddingsModelType[] = [
+  {
+    architecture: 'BertModel',
+    models: [
+      {
+        loraSupport: false,
+        links: [
+          'https://huggingface.co/BAAI/bge-small-en-v1.5',
+          'https://huggingface.co/BAAI/bge-base-en-v1.5',
+          'https://huggingface.co/BAAI/bge-large-en-v1.5',
+          'https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2',
+          'https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1',
+          'https://huggingface.co/mixedbread-ai/mxbai-embed-xsmall-v1',
+          'https://huggingface.co/WhereIsAI/UAE-Large-V1',
+        ],
+      },
+    ],
+  },
+  {
+    architecture: 'MPNetForMaskedLM',
+    models: [
+      {
+        loraSupport: false,
+        links: [
+          'https://huggingface.co/sentence-transformers/all-mpnet-base-v2',
+          'https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1',
+        ],
+      },
+    ],
+  },
+  {
+    architecture: 'RobertaForMaskedLM',
+    models: [
+      {
+        loraSupport: false,
+        links: ['https://huggingface.co/sentence-transformers/all-distilroberta-v1'],
+      },
+    ],
+  },
+  {
+    architecture: 'XLMRobertaModel',
+    models: [
+      {
+        loraSupport: false,
+        links: [
+          'https://huggingface.co/mixedbread-ai/deepset-mxbai-embed-de-large-v1',
+          'https://huggingface.co/intfloat/multilingual-e5-large-instruct',
+          'https://huggingface.co/intfloat/multilingual-e5-large',
+        ],
+      },
+    ],
+  },
+];
diff --git a/site/docs/supported-models/index.mdx b/site/docs/supported-models/index.mdx
@@ -2,6 +2,8 @@ import ImageGenerationModelsTable from './_components/image-generation-models-ta
 import LLMModelsTable from './_components/llm-models-table';
 import VLMModelsTable from './_components/vlm-models-table';
 import WhisperModelsTable from './_components/whisper-models-table';
+import TextEmbeddingsModelsTable from './_components/text-embeddings-models-table';
+import SpeechGenerationModelsTable from './_components/speech-generation-models-table';
 
 
 # Supported Models
@@ -68,6 +70,14 @@ pip install timm einops
 
 <WhisperModelsTable />
 
+## Text Embeddings Models
+
+<TextEmbeddingsModelsTable />
+
+## Speech Generation Models
+
+<SpeechGenerationModelsTable />
+
 :::info
 
 Some models may require access request submission on the Hugging Face page to be downloaded.
diff --git a/src/README.md b/src/README.md
@@ -543,7 +543,7 @@ For information on how OpenVINO™ GenAI works, refer to the [How It Works Secti
 
 ## Supported Models
 
-For a list of supported models, refer to the [Supported Models Section](../SUPPORTED_MODELS.md).
+For a list of supported models, refer to the [Supported Models](https://openvinotoolkit.github.io/openvino.genai/docs/supported-models/) page.
 
 ## Debug Log
 
