28 4 31

Fidite Nemini PRO

FiditeNemini

FiditeNemini2023

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

FiditeNemini's activity

New activity in huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 about 1 month ago

1M token context version is out

#2 opened about 1 month ago by

FiditeNemini

New activity in mkurman/Qwen2.5-14B-DeepSeek-R1-1M about 1 month ago

Merge strategy

#1 opened about 1 month ago by

FiditeNemini

New activity in aiqcamp/FLUX-VisionReply2 2 months ago

🚩 Report: Ethical issue(s)

#2 opened 2 months ago by

FiditeNemini

New activity in mlx-community/mlx-my-repo 3 months ago

🚩 Report: Not working

#30 opened 3 months ago by

southmost

New activity in ZeusLabs/Chronos-Platinum-72B 5 months ago

Really really good!

#3 opened 5 months ago by

FiditeNemini

New activity in black-forest-labs/FLUX.1-schnell 6 months ago

Not running on MacOS ComfyUI

#13 opened 7 months ago by

FiditeNemini

New activity in Kijai/flux-fp8 7 months ago

Can this model be used on Apple Silicon?

#14 opened 7 months ago by

jsmidt

New activity in qresearch/llama-3.1-8B-vision-378 7 months ago

70B?

#3 opened 7 months ago by

FiditeNemini

New activity in nDimensional/NatViS-Natural-Vision-Lightning-SDXL 7 months ago

Absolutely awesome.

#1 opened 7 months ago by

FiditeNemini

New activity in mlabonne/Llama-3.1-70B-Instruct-lorablated 7 months ago

Very nice

#2 opened 7 months ago by

FiditeNemini

New activity in qnguyen3/nanoLLaVA-1.5 8 months ago

GGUF conversion assistance?

#3 opened 8 months ago by

FiditeNemini

This model is amazing!

#1 opened 8 months ago by

nicolollo

New activity in cognitivecomputations/dolphin-vision-72b 8 months ago

Just Reviewed It

#3 opened 8 months ago by

fahdmirzac

Running on MacOS - issues with getting projector built.

#2 opened 8 months ago by

FiditeNemini

You guys are legends!!!

#1 opened 8 months ago by

FiditeNemini

New activity in gokaygokay/Florence-2-SD3-Captioner 8 months ago

Finetuning code.

#1 opened 8 months ago by

ljnlonoljpiljm

New activity in migtissera/Tess-v2.5.2-Qwen2-72B 9 months ago

Excellent model

#1 opened 9 months ago by

FiditeNemini

New activity in mradermacher/Unhinged-Qwen2-70B-GGUF 9 months ago

Thank you.

#1 opened 9 months ago by

FiditeNemini

New activity in cognitivecomputations/dolphin-2.9-llama3-70b 10 months ago

large context Dolphin Llama70b?

#6 opened 10 months ago by

Alias1964

New activity in cognitivecomputations/based-13b 10 months ago

Request: Make a Based LLaMa-3-8B and LLaMa-3-70B

#1 opened 10 months ago by

Joseph717171