Hugging Face's logo
Blair Sadewitz's picture
39 2 30

Blair Sadewitz

tachyphylaxis
Olafangensan's profile picture 21world's profile picture nbeerbower's profile picture
·

AI & ML interests

None yet

Recent Activity

replied to mlabonne's post about 1 month 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
liked a dataset about 2 months ago
tachyphylaxis/The-Mind-Is-A-Metaphor
liked a model about 2 months ago
nbeerbower/Llama3.1-Gutenberg-Doppel-70B
View all activity

Organizations

None yet

tachyphylaxis's activity

New activity in anthracite-org/magnum-v2-123b 3 months ago

This is why we need big models

4
#5 opened 3 months ago by Ainonake
New activity in bartowski/magnum-v2-123b-GGUF 3 months ago

Getting jibberisk output on Q6

1
#2 opened 3 months ago by AIGUYCONTENT
New activity in Guilherme34/Meta-Llama-3.1-70B-Chat-Uncensored 4 months ago

merged

6
#3 opened 4 months ago by tachyphylaxis
New activity in mradermacher/L3-70B-Euryale-v2.1-GGUF 6 months ago

Beyond frustrating

11
#1 opened 6 months ago by Utochi
New activity in crestf411/L3-70B-daybreak-storywriter-v0.4 6 months ago

please add these phrases to your blacklist

4
#1 opened 6 months ago by tachyphylaxis
New activity in ryzen88/Llama-3-70b-Arimas-story-RP-V1.5 6 months ago

I think you're missing a lot of the shards

1
#1 opened 6 months ago by tachyphylaxis
New activity in tdrussell/Llama-3-70B-Instruct-Storywriter 7 months ago

Nice model, but a lora / tune on the base Llama3-70B would be helpful

9
#2 opened 7 months ago by Henk717
New activity in ParasiticRogue/Merged-Vicuna-RP-Stew-34B 8 months ago

FWIW, I made some GGUF quants

11
#2 opened 9 months ago by tachyphylaxis
New activity in ParasiticRogue/Merged-Vicuna-RP-Stew-34B-4.25bpw-h6-exl2-fix 9 months ago

Which parquet are you referring to?

3
#1 opened 9 months ago by tachyphylaxis
New activity in dreamgen/opus-v1-34b-awq 9 months ago

Looks like you forgot to delete the old files (?)

1
#1 opened 9 months ago by tachyphylaxis
New activity in dreamgen/opus-v1-34b 9 months ago

jinja template for story writing

3
#3 opened 9 months ago by tachyphylaxis
New activity in TriadParty/deepsex-34b 9 months ago

FYI, I converted the model to llama
#9 opened 9 months ago by tachyphylaxis
New activity in chargoddard/Yi-34B-Llama 9 months ago

Can you share the converting code ?

5
#7 opened about 1 year ago by Q-bert
New activity in alchemonaut/QuartetAnemoi-70B-t0.0001 9 months ago

FYI: I quantized this with AutoAWQ

2
#5 opened 10 months ago by tachyphylaxis
New activity in alchemonaut/QuartetAnemoi-70B-t0.0001-GGUF 10 months ago

A good surprise

2
#1 opened 10 months ago by Nexesenex
New activity in Envoid/Fish-8x7B 10 months ago

Nephrology dataset?

4
#1 opened 10 months ago by tachyphylaxis
New activity in TriadParty/deepsex-34b 10 months ago

You have my gratitude

5
#6 opened 12 months ago by tachyphylaxis

Prompt format (history)

4
#8 opened 11 months ago by tachyphylaxis
New activity in TriadParty/deepmoney-34b-200k-base 11 months ago

Awesome model! Training parameters?

6
#1 opened 11 months ago by brucethemoose
New activity in Undi95/FlatDolphinMaid-8x7B 11 months ago

sampler, etc. settings for these MoE models

2
#1 opened 11 months ago by tachyphylaxis