Liang Chen comments

Results 15 comments of


                                            Liang Chen

⚠️ Missing texture

same problem

Add support for model training from checkpoint

Hi @Littleor I met a cuda-out-of-memory error after loading from a checkpoint before training. Do you have any idea why this happened? Training from scratch is ok.

Actual Training Loss Curve

Thanks for your information! Can you provide some math or code of calculating the E(ground_truth) from the ground truth token distribution? Is it a next-token prediction entropy?

[Feature] Multimodal agents demo

> The high-level class design looks good to me! Left one minor comment in the code. Hi, thanks for your review, yet I can't see your comment in the code....

[Feature] Multimodal agents demo

TODO: - Write document for multimodal function @chenllliang - Give an example using the multimodal prompt class @ZIYU-DEEP

[Feature] Multimodal agents demo

I have updated the documentation of multimdoal prompt class. (It could be merged I think)

[Feature] Multimodal agents demo

currently developming multimodal role-playing demo

[Feature] Multimodal agents demo

I design a pipeline for a possible application of multimodal agents' collaboartion. It's called "Scientific Graph Painter", which is used to generate python code to draw a figure from in...

[Feature Request] MultimodalPrompt

@lightaime Hi, the design is inspired by current advance in multimodal llm like MMICL and MiniGPT5, which support interleaved text and image as input. The multimodal information could appear on...

[Feature Request] MultimodalPrompt

I don't know either lol, but from the gpt4-v interface provided to user, it seems that gpt4-v simply concats the image and the text.