32 10 33

fs

failspy

failspy

AI & ML interests

None yet

Recent Activity

liked a model 30 days ago

mlabonne/gemma-3-27b-it-abliterated-GGUF

replied to mlabonne's post 6 months ago

✂️ Uncensor any LLM with abliteration I wrote an article about abliteration and how NeuralDaredevil-8B was created. Beyond removing alignment, I believe it's an interesting technique with a lot of potential. It's basically fine-tuning without retraining. In this article, we see how it works, implement it in Google Colab, and heal the abliterated model to recover the performance drop due to this technique. The final model is an uncensored and high-quality model with the highest MMLU score on the Open LLM Leaderboard (8B category). https://huggingface.co/blog/mlabonne/abliteration

upvoted a collection 7 months ago

Molmo

View all activity

Organizations

failspy's activity

New activity in failspy/Nemotron-4-340B-Instruct-SafeTensors 9 months ago

Can you share how you converted this?

#1 opened 10 months ago by

bjoernp

New activity in failspy/Nemotron-4-340B-Instruct-SafeTensors 10 months ago

Status on inference?

#2 opened 10 months ago by

ZQ-Dev

New activity in nvidia/Nemotron-4-340B-Instruct 10 months ago

Add to HF Inference APIs

#4 opened 10 months ago by

mrfakename

New activity in failspy/Phi-3-mini-4k-geminified 11 months ago

tokenizer.model 0 bytes?

#2 opened 11 months ago by

beijinghouse

New activity in failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5-GGUF 11 months ago

unknown pre-tokenizer type: 'smaug-bpe'

#1 opened 11 months ago by

kep359

New activity in failspy/Phi-3-vision-128k-instruct-abliterated-alpha 11 months ago

Still get refusals.

#1 opened 11 months ago by

jackboot

New activity in failspy/Phi-3-mini-4k-geminified 11 months ago

The model card unclear xD

#1 opened 11 months ago by

Erilaz

New activity in failspy/Llama-3-70B-Instruct-abliterated-v3-GGUF 11 months ago

Splitting ggufs

#1 opened 11 months ago by

Jobaar

New activity in failspy/kappa-3-phi-abliterated 11 months ago

Ablation Code release

#1 opened 11 months ago by

failspy

New activity in failspy/Phi-3-medium-4k-instruct-abliterated-v3-GGUF 11 months ago

WizardLM-2-8x22B abliteration inquiry

#1 opened 11 months ago by

OrangeApples

New activity in failspy/Phi-3-medium-4k-instruct-abliterated-v3 11 months ago

Upload 2 files

#1 opened 11 months ago by

TheDrummer

New activity in failspy/Llama-3-70B-Instruct-abliterated-v3 11 months ago

What is new in V3 version?

#1 opened 11 months ago by

zypcastles

New activity in cognitivecomputations/Dolphin-2.9.1-Phi-3-Kensho-4.5B 11 months ago

Is this "dolphin" uncensored?

#2 opened 11 months ago by

scubadrv

New activity in cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2 11 months ago

Hallucinations?

#1 opened 11 months ago by deleted

New activity in failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 11 months ago

Possibly missing files

#2 opened 11 months ago by

ayyylol

New activity in failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3 11 months ago

missing tokenizer?

#1 opened 11 months ago by

mradermacher

New activity in failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 11 months ago

GGUF version

#1 opened 11 months ago by

epigene

New activity in failspy/Llama-3-8B-Instruct-abliterated 11 months ago

Update eos_token

#2 opened 11 months ago by

ayyylol

New activity in cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2 11 months ago

Update tokenizer_config.json

#3 opened 11 months ago by

ayyylol

New activity in failspy/llama-3-70B-Instruct-abliterated 11 months ago

Trying to reproduce results

#9 opened 11 months ago by

noisefloordev