Nina Beerbower's picture

Nina Beerbower PRO

nbeerbower

·

https://ko-fi.com/birubawa

AI & ML interests

QLoRA finetuning and merging LLMs for fun. Also learning about diffusion and VLMs!

Recent Activity

updated a model about 2 hours ago

nbeerbower/Huihui-Qwen3.5-27B-abliterated-Athanorlite-ORPO

published a model about 2 hours ago

nbeerbower/Huihui-Qwen3.5-27B-abliterated-Athanorlite-ORPO

liked a model 1 day ago

mradermacher/Huihui-Qwen3.5-9B-abliterated-TIES-Hemlock-SFT-GGUF

View all activity

Organizations

upvoted 2 collections 2 months ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 106 items • Updated about 1 hour ago • 45

Qwen3-TTS

7 items • Updated Jan 22 • 336

upvoted a collection 3 months ago

Hermes 4 Collection

9 items • Updated 29 days ago • 92

upvoted 2 collections 4 months ago

Cerebras REAP

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 134

Olmo 3

Artifacts for the Olmo 3 release. • 7 items • Updated 29 days ago • 167

upvoted a collection 5 months ago

VellumForge2 Datasets

A collection of fantasy writing datasets generated by the VellumForge2 tool • 7 items • Updated 29 days ago • 4

upvoted 2 collections 6 months ago

Qwen3-VL-abliterated

14 items • Updated 29 days ago • 31

Qwen3-VL

37 items • Updated Dec 31, 2025 • 676

upvoted a collection 9 months ago

SmolLM3 pretraining datasets

datasets used in SmolLM3 pretraining • 15 items • Updated Aug 12, 2025 • 45

upvoted a collection 11 months ago

Qwen2.5-CensorTune

2 items • Updated 29 days ago • 1

upvoted a paper about 1 year ago

Modifying Large Language Model Post-Training for Diverse Creative Writing

Paper • 2503.17126 • Published Mar 21, 2025 • 36

upvoted 5 collections about 1 year ago

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text. • 2 items • Updated Mar 20, 2025 • 98

Datasets - Reasoning

5 items • Updated 29 days ago • 2

🧠 Reasoning datasets

Datasets with reasoning traces for math and code released by the community • 24 items • Updated May 19, 2025 • 187

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 10 items • Updated 29 days ago • 559

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated Dec 31, 2025 • 126

upvoted an article about 1 year ago

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

823

upvoted 2 collections over 1 year ago

Tulu 3 Datasets

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 32 items • Updated 29 days ago • 96

Resources for Tagging / Captioning / Prompting / LLM

9974 items • Updated 1 day ago • 6

upvoted an article almost 2 years ago

Article

Fine-tune Llama 3 with ORPO

Apr 22, 2024

•

240