transformers.js

e848907e - Add new models (Janus, Qwen2-VL, JinaCLIP, LLaVA-OneVision, ViTPose, MGP-STR) & refactor processors. (#1001)

Add new models (Janus, Qwen2-VL, JinaCLIP, LLaVA-OneVision, ViTPose, MGP-STR) & refactor processors. (#1001) * Extract processor classes into separate folders * Fix typo * Define which classes use `processor_config.json` * [WIP] Add support for `deepseek-ai/Janus-1.3B` * Fix unit tests * Remove redundant `extends` JSDoc * Fix JSDoc * Update Janus JSDoc * Improve `VLChatProcessor` processor types * Expose ImageFeatureExtractor as copy of ImageProcessor * Add support for `LLaVA-OneVision` * Add support for ViTPose * Add ViTPose to README * Bump dependencies * Add support for `MGP-STR` models * Documentation fixes * Add support for `Qwen2VLImageProcessor` * Format tests folder * Use `AutoImageProcessor` for image processors * Add support for `Qwen2VLProcessor` * Fix `image_grid_thw` dtype * Fix bigint product * [WIP] Support for qwen2vl models * Add support for JinaCLIP models * Add listed support for Janus * Fix qwen2vl processor unit test * Update dependency versions * Export logits processors * Expose batch_decode for processor * Qwen2VL - Implement `get_rope_index` * Add `Qwen2VLForConditionalGeneration` unit tests * Update dependencies * Update `onnxslim==0.1.42` * `tokenizer.default_chat_template` has been removed * Add listed support for Qwen2-VL * Fix `.from_pretrained` function type