nicolo's picture

nicolo

nicolollo

·

AI & ML interests

None yet

Recent Activity

liked a model 5 days ago

nomic-ai/nomic-embed-text-v2-moe

reacted to grimjim's post with ❤️ 7 days ago

This recent paper points to an explanation for the unreasonable effectiveness of Frankenmerges: https://huggingface.co/papers/2502.05171 Specifically, the duplication of layers in Frankenmerges serves a purpose similar to what occurs in their recurrent-depth architecture. Successful frankenmerges that operate without additional fine-tuning are able to recover or "heal" from any damage due to abrupt transitions between layer blocks. Operational replicated layer blocks can provide functional benefits grounded in latent reasoning. Frankenmerges can also result in hybrid reasoning, by splicing together the latent reasoning of different models. Back in April 2024, I was able to duplicate a few layers in the Llama 3 8B model, turning it into a 9B model, without harming benchmarks significantly, despite any transition damage. https://huggingface.co/grimjim/llama-3-experiment-v1-9B My informal experimentation suggested that latent reasoning circuits could occupy continguous stacks of 2-4 layers, though the result was highly sensitive to the choice of transition location between layers.

liked a model 7 days ago

tomg-group-umd/huginn-0125

View all activity

Organizations

models 4

nicolollo/test1-Q4_K_M-GGUF

Updated 27 days ago • 33

nicolollo/test1

Updated 27 days ago • 13

nicolollo/test-Q4_K_M-GGUF

Updated Dec 28, 2024 • 9

nicolollo/test

Updated Dec 28, 2024 • 5

datasets 2

nicolollo/my-distiset

Viewer • Updated Sep 16, 2024 • 1 • 82

nicolollo/docci

Viewer • Updated Jul 11, 2024 • 14.7k • 214