Maybe it will be better if you focused more at the research rather than doing such things. Our website it not optimised for mobile users as it has more explanation to do rather than just make visitors feel good. Good luck with the things you are going.
What is the point of using a outright ancient model like DeepSeek-R1-Distill-1.5B from 2025 based on another ancient model like Qwen2.5-Math-1.5B from 2024, when a much better modern model like LFM3-1.7B exists?
This is a well known tell for using (bad) models to do "research". They always use qwen2.5 and R1, because of the amount of "news" that the two models received. So the models "suggest" those lineages a lot. The local llama sub used to get a few of these a day. That and a zenodo "paper" link are clear tells of badly written stuff.
Concretely, if you start with, say, a 1.5 or 4 bit quant, then run this, you get something the size of a 0.5 - 1.5 bits without further degradation in model behavior?
Would be interesting if one could verify any of these claims via the reputation of any of the research participants.
As it stands, everything credits "NeuraCryption Private Limited" which was registered very recently [0][1][2] to an adress that is shared by several other recently registered businesses [scroll down on 0], and this is their very first offering according to the zenodo link they provided [3]
Further, looking at the code, it appears to be a standard quanitizer...
Like...there is no existing method by which one could genuinely compress a tens of GB weights file in to a third the space using only 50mb of RAM.
I’ll probably get downvoted but the site is AI slop filled with math and issues that I guarantee the OP does not understand (based on, for example, the OP claiming a trillion parameter model can be compressed to be under 50 MB with near lossless performance).
Hmm, this claims "functionally lossless" compression over 3x. But where is the starting point? Bf16 of fp16? If so, how much better is it than current quantization techniques?
This should be tested on a medium size dense model. For example Qwen3.8-27B. How much better is it t than quantization to 4.5 bits?
24 comments
[ 0.27 ms ] story [ 13.9 ms ] thread- gradient headline
- random vertical scrollbar on mobile
- fingernail cards
If UI is not your area or priority, that's ok. Why not just post an Arxiv link?
“We didn't just build an AI voice bot. We engineered a full-stack autonomous AI call center platform with quick call center setup in 3 minutes.”
Concretely, if you start with, say, a 1.5 or 4 bit quant, then run this, you get something the size of a 0.5 - 1.5 bits without further degradation in model behavior?
Any claims about throwing away 2/3rds of the model weights (not just quantizing them) and maintaining “near lossless” quality are simply false.
I clicked on the benchmarks page expecting some quality benchmarks but only saw speed benchmarks before I gave up and stopped scrolling.
The claims don’t even make sense. It’s showing “100% GPU resident” for a model of a size that cannot fit into the GPU.
As it stands, everything credits "NeuraCryption Private Limited" which was registered very recently [0][1][2] to an adress that is shared by several other recently registered businesses [scroll down on 0], and this is their very first offering according to the zenodo link they provided [3]
Further, looking at the code, it appears to be a standard quanitizer...
Like...there is no existing method by which one could genuinely compress a tens of GB weights file in to a third the space using only 50mb of RAM.
[0]https://www.zaubacorp.com/NEURACRYPTION-PRIVATE-LIMITED-U620...
[1]https://www.registerkaro.in/company/neuracryption-private-li...
[2]https://www.falconebiz.com/company/NEURACRYPTION-PRIVATE-LIM...
[3]https://zenodo.org/search?q=metadata.creators.person_or_org....
This should be tested on a medium size dense model. For example Qwen3.8-27B. How much better is it t than quantization to 4.5 bits?