Bagel: Open-source unified multimodal model
bagel-ai.org
Bagel: Open-source unified multimodal model
1–10 of 35 posts
Re: Bagel: Open-source unified multimodal model
#2I couldn’t find it, what are the hardware expectations for bagel?
Re: Bagel: Open-source unified multimodal model
#3I couldn’t find it, what are the hardware expectations for bagel?
If you follow the hugginface link at the bottom you get to te actual model. Here https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT
It seems to be 7b, but like with other new architectures expect to not be able to run it quantizised.
Re: Bagel: Open-source unified multimodal model
#4I couldn’t find it, what are the hardware expectations for bagel?
If the model uses FP16 precision and has 7 billion active parameters, it would require approximately 14 GB of VRAM. I didn't read the paper.
Re: Bagel: Open-source unified multimodal model
#5These days, papers come with an advertisement video
Re: Bagel: Open-source unified multimodal model
#6Re: Bagel: Open-source unified multimodal model
#7Earlier quoted context omitted.
If the model uses FP16 precision and has 7 billion active parameters, it would require approximately 14 GB of VRAM. I didn't read the paper.
How can you calculate required VRAM from precision and parameter number?
A float16 is 2 bytes. 7B * 2 bytes = 14GB. I can't say if that's an accurate number, but that's almost certainly how tonii141 calculated it.
Re: Bagel: Open-source unified multimodal model
#8Earlier quoted context omitted.
How can you calculate required VRAM from precision and parameter number?
A float16 is 2 bytes. 7B * 2 bytes = 14GB. I can't say if that's an accurate number, but that's almost certainly how tonii141 calculated it.
Oh, so FP16 means FloatingPoint16? I'm glad to learn something today, thanks!
Re: Bagel: Open-source unified multimodal model
#9These days, papers come with an advertisement video
As someone who used to be in the academia, I think is isn't bad in itself, I just worry that by comparison it raises the burden of effort that one has to make in order to get their work noticed.
Re: Bagel: Open-source unified multimodal model
#10The demo shows pretty weak performance compared to other small models. It misunderstood my question due to picking an uncommon way to interpret it. After clarifying what I wanted it lost all context I had provided in the previous message. My benchmark query intentionally ambiguous and I use it to see how models handle ambiguity, handle information which can be outdated, and handle avoiding hallucination. Usually weak models will just hallucinate an answer, but this model was the first who want able to understand the question.