llama4 release discussion thread
-
General consensus seems to be that llama4 was a flop. A head of meta AI research division was let go.
Do you think it was a bad fp32 conversion, or just unerwhelming models all around?
2t parameters was a big increase without much gain. If throwing compute and parameters isnt working to stay competitive anymore, how do you think the next big performance gains will be made? Better CoT reasoning patterns? Omnimodal? something entirely new?
-
General consensus seems to be that llama4 was a flop. A head of meta AI research division was let go.
Do you think it was a bad fp32 conversion, or just unerwhelming models all around?
2t parameters was a big increase without much gain. If throwing compute and parameters isnt working to stay competitive anymore, how do you think the next big performance gains will be made? Better CoT reasoning patterns? Omnimodal? something entirely new?
I think the next bit of performance may be leaning hard into QAT. We know there is a lot of wasted precision in models, so the more we understand that during training the better quality small quants can get.
I also think diffusion LLMs ability to change previous tokens is amazing. As well as the ability to iteratively use an auto regressive LLM to increase output quality.
I think a mix of QAT and iterative interference will bring the biggest upgrades to local use. It'll give you a smaller higher quality model thay you can decide to run for even longer for higher quality outputs.
-
I think the next bit of performance may be leaning hard into QAT. We know there is a lot of wasted precision in models, so the more we understand that during training the better quality small quants can get.
I also think diffusion LLMs ability to change previous tokens is amazing. As well as the ability to iteratively use an auto regressive LLM to increase output quality.
I think a mix of QAT and iterative interference will bring the biggest upgrades to local use. It'll give you a smaller higher quality model thay you can decide to run for even longer for higher quality outputs.
Hmmn, never heard of QAT. What does it stand for?
-
Hmmn, never heard of QAT. What does it stand for?
https://pytorch.org/blog/quantization-aware-training/
I had heard of it but I'm not aware of public models implementing this
-
https://pytorch.org/blog/quantization-aware-training/
I had heard of it but I'm not aware of public models implementing this
Here is link for ollama for Gemma 3 QAT
https://ollama.com/eramax/gemma-3-27b-it-qat:q4_0There are ggufs around if you want to try it on another back end.
-
System shared this topic on
-
Here is link for ollama for Gemma 3 QAT
https://ollama.com/eramax/gemma-3-27b-it-qat:q4_0There are ggufs around if you want to try it on another back end.
Thanks. I'll try it out!
