-
### 🐛 Describe the bug
### Bug Description
Whenever DDP used with IterableDataset, if data is not distributed in equal sizes across all ranks (gpus), then on some ranks loss is not calculated for …
-
### Proposal summary
## Feature Request
Enable Opik to display additional media formats, including audio, PDF, and video.
## Background
Opik currently supports only image display, which li…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
I want to build a multimodal chat using streamlit and llamaindex workflows, wherein user…
-
### 🚀 The feature, motivation and pitch
***Please note that since the actual implementation is going to be simple, and the design has already been reviewed, the purpose of this GitHub Issue is to l…
-
## 概要
人間は何かを説明する時にあらゆる五感情報からそれに対する抽象的なイメージを頭に浮かべて説明している。
マルチモーダルな入力においてはそれが可能。
出力に関してもマルチモーダルに振る舞うことがわかる。
それらが全てわかるようなデモとなっている。
## ポイント
- テキストだけでは不十分な情報を補って説明することができる。
- 言語化したものを画像や音声など…
-
**Is your feature request related to a problem? Please describe.**
I'm frustrated when I can't use multimodal models like "gpt-4-vision-preview" in Cheshire-cat-ai to process and retrieve information…
-
We have built-in pre-process function for bedrock multi-modal model `connector.pre_process.bedrock.multimodal_embedding` since OS 2.16
Post process function: `connector.post_process.bedrock.embedding…
-
**Bug Description:**
The `vendor_multimodal_model_name` parameter does not seem to work as expected when using the `openai-gpt4o` model and vendor_multimodal_api_key
-
### Your current environment
```text
The output of `python collect_env.py`
```
### How would you like to use vllm
I want to run inference of [ColPali](https://huggingface.co/vidore/colpali). I …
-