Skip to content

Commit b0bdfd5

Browse files
msluszniakmsluszniak
authored
docs: align model backend tables with the registry (#1435)
## Description Regenerated every `Supported Backends` cell from `models.ts` and fixed the rows that disagreed with what the library actually resolves. | Page | Row | Was | Now | | --- | --- | --- | --- | | LLM | Llama 3.2, Qwen 3, Qwen 2.5, Hammer 2.1, Phi-4 Mini | XNNPACK | XNNPACK, MLX | | LLM | Liquid LFM 2.5 | one row, credited Vulkan to the text models | split text / VL, Vulkan on VL only | | LLM | SmolLM2 135M/360M/1.7B | missing | XNNPACK, MLX | | Keypoints | RF-DETR Keypoint | XNNPACK, Core ML, MLX | XNNPACK, Core ML | | Text embeddings | multi-qa | one row, credited Core ML to mpnet | split MiniLM / mpnet | After the change every one of the 104 registry models is reachable from a docs row and no cell claims a backend the registry does not ship. ### Introduces a breaking change? - [ ] Yes - [x] No ### Type of change - [ ] Bug fix (change which fixes an issue) - [ ] New feature (change which adds functionality) - [x] Documentation update (improves or adds clarity to existing documentation) - [ ] Other (chores, tests, code style improvements etc.) ### Tested on - [ ] iOS - [ ] Android ### Testing instructions Docs only. Backend cells were diffed against `models.ts` on `main` by a script, and sizes for the new SmolLM2 and split LFM 2.5 rows come from `HEAD` on the HuggingFace artifacts at `resolve/v0.10.0`. ### Related issues #556 ### Checklist - [x] I have performed a self-review of my code - [ ] I have commented my code, particularly in hard-to-understand areas - [x] I have updated the documentation accordingly - [x] My changes generate no new warnings
1 parent e12ab1e commit b0bdfd5

3 files changed

Lines changed: 27 additions & 24 deletions

File tree

‎docs/docs/02-extensions/computer-vision/04-pose-and-keypoints.md‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -185,11 +185,11 @@ See [Worklets & Threading](../../03-core-and-advanced/06-worklets-and-threading.
185185

186186
The library provides ready-to-use pose and landmark detectors from the [Software Mansion HuggingFace Pose Estimation Collection](https://huggingface.co/collections/software-mansion/keypoint-detection), available in [`models.keypointDetection`](../../06-api-reference/variables/models.md#keypointdetection):
187187

188-
| Model Family | Variants | Keypoints Detected | Size Range | Supported Backends | Notes |
189-
| :---------------------- | :--------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------- | :------------------ | :------------------------------------------ | :-------------------------------------------------------------------------------------------- |
190-
| **MediaPipe BlazeFace** | [See](../../06-api-reference/variables/models.md#keypointdetectionblazeface) | [`BLAZEFACE_LANDMARKS`](../../06-api-reference/variables/BLAZEFACE_LANDMARKS.md) (6 facial landmarks + box) | 0.6 MB | XNNPACK (CPU) | Ultra-lightweight face bounding box & eye/ear/nose/mouth keypoint tracking (sub-millisecond). |
191-
| **YOLO26 Pose** | [See](../../06-api-reference/variables/models.md#keypointdetectionyolo26_pose) | [`COCO_LANDMARKS`](../../06-api-reference/variables/COCO_LANDMARKS.md) (17 body keypoints) | 11.4 MB | XNNPACK (CPU), Core ML (Apple) | Real-time multi-person full-body skeletal tracking across multiple input resolutions. |
192-
| **RF-DETR Keypoint** | [See](../../06-api-reference/variables/models.md#keypointdetectionrfdetr_keypoint) | [`COCO_LANDMARKS`](../../06-api-reference/variables/COCO_LANDMARKS.md) (17 body keypoints) | 138.6 MB – 140.9 MB | XNNPACK (CPU), Core ML (Apple), MLX (Apple) | High-accuracy body keypoint detection transformer for complex, occluded poses. |
188+
| Model Family | Variants | Keypoints Detected | Size Range | Supported Backends | Notes |
189+
| :---------------------- | :--------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------- | :------------------ | :----------------------------- | :-------------------------------------------------------------------------------------------- |
190+
| **MediaPipe BlazeFace** | [See](../../06-api-reference/variables/models.md#keypointdetectionblazeface) | [`BLAZEFACE_LANDMARKS`](../../06-api-reference/variables/BLAZEFACE_LANDMARKS.md) (6 facial landmarks + box) | 0.6 MB | XNNPACK (CPU) | Ultra-lightweight face bounding box & eye/ear/nose/mouth keypoint tracking (sub-millisecond). |
191+
| **YOLO26 Pose** | [See](../../06-api-reference/variables/models.md#keypointdetectionyolo26_pose) | [`COCO_LANDMARKS`](../../06-api-reference/variables/COCO_LANDMARKS.md) (17 body keypoints) | 11.4 MB | XNNPACK (CPU), Core ML (Apple) | Real-time multi-person full-body skeletal tracking across multiple input resolutions. |
192+
| **RF-DETR Keypoint** | [See](../../06-api-reference/variables/models.md#keypointdetectionrfdetr_keypoint) | [`COCO_LANDMARKS`](../../06-api-reference/variables/COCO_LANDMARKS.md) (17 body keypoints) | 138.6 MB – 140.9 MB | XNNPACK (CPU), Core ML (Apple) | High-accuracy body keypoint detection transformer for complex, occluded poses. |
193193

194194
:::tip Using Custom Models
195195
To use your own fine-tuned pose or landmark detection `.pte` model, pass a [`KeypointDetectorModel`](../../06-api-reference/type-aliases/KeypointDetectorModel.md) configuration object to [`useKeypointDetector`](../../06-api-reference/functions/useKeypointDetector.md) or [`createKeypointDetector`](../../06-api-reference/functions/createKeypointDetector.md):

‎docs/docs/02-extensions/natural-language/02-llm-chat-and-generation.md‎

Lines changed: 12 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -309,16 +309,18 @@ While [`useLLMChatSession`](../../06-api-reference/functions/useLLMChatSession.m
309309

310310
The library provides ready-to-use models from the [Software Mansion HuggingFace LLM Collection](https://huggingface.co/collections/software-mansion/llm-multimodal), pre-packaged with their tokenizers and Jinja chat templates in [`models.llm`](../../06-api-reference/variables/models.md#llm):
311311

312-
| Model Family | Variants | Size Range | Supported Backends | Notes |
313-
| :----------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------- | :------------------------------------------- | :-------------------------------------------------------------------------- |
314-
| **Liquid LFM 2.5** | [`350M`](../../06-api-reference/variables/models.md#llmlfm2_5_350m), [`1.2B`](../../06-api-reference/variables/models.md#llmlfm2_5_1_2b), [`VL 450M`](../../06-api-reference/variables/models.md#llmlfm2_5_vl_450m), [`VL 1.6B`](../../06-api-reference/variables/models.md#llmlfm2_5_vl_1_6b) | 265 MB – 2.43 GB | XNNPACK (CPU), MLX (Apple), Vulkan (Android) | Fast hybrid RNN/Transformer for low-latency chat & visual reasoning. |
315-
| **Meta Llama 3.2** | [`1B`](../../06-api-reference/variables/models.md#llmllama3_2_1b), [`3B`](../../06-api-reference/variables/models.md#llmllama3_2_3b) | 1.06 GB – 5.99 GB | XNNPACK (CPU) | High-quality reasoning, summarization, and instruction following. |
316-
| **Google Gemma 4** | [`E2B`](../../06-api-reference/variables/models.md#llmgemma4_e2b) | 2.45 GB – 2.70 GB | XNNPACK (CPU), MLX (Apple), Vulkan (Android) | High-fidelity instruction following from Google DeepMind research. |
317-
| **Alibaba Qwen 3** | [`0.6B`](../../06-api-reference/variables/models.md#llmqwen3_0_6b), [`1.7B`](../../06-api-reference/variables/models.md#llmqwen3_1_7b), [`4B`](../../06-api-reference/variables/models.md#llmqwen3_4b) | 482 MB – 7.49 GB | XNNPACK (CPU) | Next-gen compact multilingual models supporting 29+ languages. |
318-
| **Alibaba Qwen 2.5** | [`0.5B`](../../06-api-reference/variables/models.md#llmqwen2_5_0_5b), [`1.5B`](../../06-api-reference/variables/models.md#llmqwen2_5_1_5b), [`3B`](../../06-api-reference/variables/models.md#llmqwen2_5_3b) | 417 MB – 5.75 GB | XNNPACK (CPU) | Proven multilingual instruction models across code, math, and chat. |
319-
| **Hammer 2.1** | [`0.5B`](../../06-api-reference/variables/models.md#llmhammer2_1_0_5b), [`1.5B`](../../06-api-reference/variables/models.md#llmhammer2_1_1_5b), [`3B`](../../06-api-reference/variables/models.md#llmhammer2_1_3b) | 398 MB – 5.75 GB | XNNPACK (CPU) | Fine-tuned function calling for automated tool execution & structured JSON. |
320-
| **Microsoft Phi-4 Mini** | [`3.8B`](../../06-api-reference/variables/models.md#llmphi4_mini) | 2.62 GB – 7.15 GB | XNNPACK (CPU) | High-density reasoning model for STEM problem solving & coding. |
321-
| **SpeakLeash Bielik v3** | [`1.5B`](../../06-api-reference/variables/models.md#llmbielik_v3_1_5b) | 923 MB – 2.97 GB | XNNPACK (CPU) | Bilingual Polish & English instruction model. |
312+
| Model Family | Variants | Size Range | Supported Backends | Notes |
313+
| :----------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------- | :------------------------------------------- | :-------------------------------------------------------------------------- |
314+
| **Liquid LFM 2.5** | [`350M`](../../06-api-reference/variables/models.md#llmlfm2_5_350m), [`1.2B`](../../06-api-reference/variables/models.md#llmlfm2_5_1_2b) | 265 MB – 2.43 GB | XNNPACK (CPU), MLX (Apple) | Fast hybrid RNN/Transformer for low-latency chat. |
315+
| **Liquid LFM 2.5 VL** | [`VL 450M`](../../06-api-reference/variables/models.md#llmlfm2_5_vl_450m), [`VL 1.6B`](../../06-api-reference/variables/models.md#llmlfm2_5_vl_1_6b) | 376 MB – 2.36 GB | XNNPACK (CPU), MLX (Apple), Vulkan (Android) | Vision-language variants for image understanding and visual reasoning. |
316+
| **Meta Llama 3.2** | [`1B`](../../06-api-reference/variables/models.md#llmllama3_2_1b), [`3B`](../../06-api-reference/variables/models.md#llmllama3_2_3b) | 1.06 GB – 5.99 GB | XNNPACK (CPU), MLX (Apple) | High-quality reasoning, summarization, and instruction following. |
317+
| **Google Gemma 4** | [`E2B`](../../06-api-reference/variables/models.md#llmgemma4_e2b) | 2.45 GB – 2.70 GB | XNNPACK (CPU), MLX (Apple), Vulkan (Android) | High-fidelity instruction following from Google DeepMind research. |
318+
| **Alibaba Qwen 3** | [`0.6B`](../../06-api-reference/variables/models.md#llmqwen3_0_6b), [`1.7B`](../../06-api-reference/variables/models.md#llmqwen3_1_7b), [`4B`](../../06-api-reference/variables/models.md#llmqwen3_4b) | 482 MB – 7.49 GB | XNNPACK (CPU), MLX (Apple) | Next-gen compact multilingual models supporting 29+ languages. |
319+
| **Alibaba Qwen 2.5** | [`0.5B`](../../06-api-reference/variables/models.md#llmqwen2_5_0_5b), [`1.5B`](../../06-api-reference/variables/models.md#llmqwen2_5_1_5b), [`3B`](../../06-api-reference/variables/models.md#llmqwen2_5_3b) | 417 MB – 5.75 GB | XNNPACK (CPU), MLX (Apple) | Proven multilingual instruction models across code, math, and chat. |
320+
| **Hammer 2.1** | [`0.5B`](../../06-api-reference/variables/models.md#llmhammer2_1_0_5b), [`1.5B`](../../06-api-reference/variables/models.md#llmhammer2_1_1_5b), [`3B`](../../06-api-reference/variables/models.md#llmhammer2_1_3b) | 398 MB – 5.75 GB | XNNPACK (CPU), MLX (Apple) | Fine-tuned function calling for automated tool execution & structured JSON. |
321+
| **Microsoft Phi-4 Mini** | [`3.8B`](../../06-api-reference/variables/models.md#llmphi4_mini) | 2.62 GB – 7.15 GB | XNNPACK (CPU), MLX (Apple) | High-density reasoning model for STEM problem solving & coding. |
322+
| **HuggingFace SmolLM2** | [`135M`](../../06-api-reference/variables/models.md#llmsmollm2_135m), [`360M`](../../06-api-reference/variables/models.md#llmsmollm2_360m), [`1.7B`](../../06-api-reference/variables/models.md#llmsmollm2_1_7b) | 158 MB – 1.83 GB | XNNPACK (CPU), MLX (Apple) | Smallest footprint family, for constrained devices and fast drafting. |
323+
| **SpeakLeash Bielik v3** | [`1.5B`](../../06-api-reference/variables/models.md#llmbielik_v3_1_5b) | 923 MB – 2.97 GB | XNNPACK (CPU) | Bilingual Polish & English instruction model. |
322324

323325
:::tip Using Custom Models
324326
To use your own fine-tuned LLM `.pte` model, pass an [`LLMModel`](../../06-api-reference/type-aliases/LLMModel.md) configuration object to [`useLLMChatSession`](../../06-api-reference/functions/useLLMChatSession.md) or [`createLLMChatSession`](../../06-api-reference/functions/createLLMChatSession.md):

0 commit comments

Comments
 (0)