Hugging Face's logo
Fidite Nemini's picture
28 4 31

Fidite Nemini PRO

FiditeNemini
neoopus's profile picture jott1970's profile picture swingnoah's profile picture
·

AI & ML interests

Prompt engineering, unalignment, MLX, model merging, diffusion models

Recent Activity

reacted to luigi12345's post with 👍 10 days ago
✅BEST DEBUG PROMPT Language: Any. 🌀Project Type: Any ``` What prompt if sent to you will make you detect and fix all the code crashing issues in the COMPLETE codebase so I don't have to ask you to fix again and again ? Step 1. Gimme such prompt Step 2 Follow it yourself quietly and COMPLETELY Step3: State that if you are asked again about finding fatal bugs and logic issues and inconsistencies in the current codebase you would not be able to find more. (You cannot lie, so you must make all the code adjustments necessary prior to such statement). ```
reacted to grimjim's post with 👍 15 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 dataset 28 days ago
cognitivecomputations/dolphin-r1
View all activity

Organizations

Fidite Nemini Open Source's profile picture MLX Community's profile picture Cognitive Computations's profile picture

datasets

None public yet