John6666 (John Smith)

upvoted a collection 21 minutes ago

Minitron 8B Derivative

Collection

Derived from the Nemo minitron 8B prune. • 2 items • Updated about 1 hour ago • 1

upvoted an article about 1 hour ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

1 day ago

• 69

upvoted a collection about 13 hours ago

spaces

Collection

5 items • Updated about 13 hours ago • 1

upvoted a collection about 18 hours ago

Multi-Modal Model

Collection

12 items • Updated about 20 hours ago • 1

upvoted a collection about 21 hours ago

S.T.E.M. - ShargeGPT

Collection

Just a collection of some datasets in shareGPT • 11 items • Updated 1 day ago • 2

upvoted a paper about 21 hours ago

OSV: One Step is Enough for High-Quality Image to Video Generation

Paper • 2409.11367 • Published 1 day ago • 10

upvoted 2 collections about 23 hours ago

Japanese ASR Models

Collection

Japanese ASR Models • 5 items • Updated 1 day ago • 2

Kotoba-Whisper

Collection

A collection of kotoba-whisper models. • 8 items • Updated about 18 hours ago • 2

upvoted a collection 1 day ago

Kurage

Collection

Multipurpose RAG models for many languages • 13 items • Updated 2 days ago • 1

upvoted a paper 1 day ago

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Paper • 2402.12875 • Published Feb 20 • 7

upvoted 4 collections 1 day ago

upvoted a collection 2 days ago

Portfolio

Collection

My favorite things that I've done, and the models I'd recommend anybody to use. • 4 items • Updated 2 days ago • 1

upvoted a paper 2 days ago

InstantDrag: Improving Interactivity in Drag-based Image Editing

Paper • 2409.08857 • Published 5 days ago • 21

upvoted an article 2 days ago

Article

Introducing Community Tools

3 days ago

• 17

upvoted 2 collections 2 days ago

DanTagGen

Collection

Danbooru Tag-based prompt Generator • 5 items • Updated May 1 • 4

Kohaku XL

Collection

Kohaku series SDXL anime base model • 9 items • Updated 15 days ago • 6

upvoted 3 articles 3 days ago

Article

Fine-tuning Parler TTS on a Specific Language

By

•

3 days ago

• 12

Article

Training Flux Locally on Mac

By

•

7 days ago

• 9

Article

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

By

•

12 days ago

• 11

upvoted 2 collections 3 days ago

Experimental

Collection

Anything marked here may not be upto my quality standards/May be incomplete and not have full sources. Or it's literal meme-merges • 13 items • Updated 2 days ago • 1

Main releases

Collection

7 items • Updated 2 days ago • 1

upvoted a collection 4 days ago

Highlighted work

Collection

My "greatest hits", sort of • 7 items • Updated 3 days ago • 4

upvoted a paper 4 days ago

TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder

Paper • 2409.08248 • Published 6 days ago • 11

upvoted an article 4 days ago

Article

Explaining the SDXL latent space

By

•

May 20

• 29

upvoted a collection 4 days ago

Barcenas Cartas y Compresión Barcenas

Collection

2 items • Updated 5 days ago • 1

upvoted a paper 4 days ago

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

Paper • 2406.07394 • Published Jun 11 • 21

upvoted an article 5 days ago

Article

In-browser LLM app in pure Python: Gemini Nano + Gradio-Lite

By

•

Jul 12

• 8

upvoted 5 collections 5 days ago

UpScale / Enhancers

Collection

6 items • Updated about 12 hours ago • 6

ImageNet 1K

Collection

ILSVRC's 2012 ImageNet 1K Subset (1.43M images,) Optimized for 🤗 Datasets / 🥐 Croissant, with Pre-Cropped and Scaled Versions • 5 items • Updated 4 days ago • 2

Fireball Llama collections

Collection

Llama collections • 3 items • Updated 11 days ago • 1

small models

Collection

4 items • Updated 29 days ago • 1

roleplay models

Collection

32 items • Updated Apr 11 • 1

upvoted 2 articles 5 days ago

Article

Accelerate 1.0.0

6 days ago

• 29

Article

"Diffusers Image Fill" guide

By

•

5 days ago

• 17

upvoted 2 papers 6 days ago

GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering

Paper • 2409.06595 • Published 8 days ago • 37

LinFusion: 1 GPU, 1 Minute, 16K Image

Paper • 2409.02097 • Published 15 days ago • 31

upvoted a collection 6 days ago

Working Merge in my Profile

Collection

9 items • Updated 6 days ago • 1

upvoted a paper 6 days ago

Multi-Head Mixture-of-Experts

Paper • 2404.15045 • Published Apr 23 • 58

upvoted a collection 6 days ago

Violet Twilight

Collection

Merge of Crimson Dawn and Azure Dusk • 7 items • Updated 5 days ago • 2

upvoted a paper 6 days ago

Ruri: Japanese General Text Embeddings

Paper • 2409.07737 • Published 7 days ago • 5

upvoted a collection 6 days ago

NanoLM

Collection

a collection of nano LMs • 13 items • Updated 7 days ago • 4

upvoted 4 papers 6 days ago

VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos

Paper • 2409.07450 • Published 7 days ago • 9

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Paper • 2409.04109 • Published 13 days ago • 36

PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation

Paper • 2409.06820 • Published 8 days ago • 54

LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Paper • 2409.06666 • Published 8 days ago • 49

upvoted 2 collections 6 days ago

Waifu of the Week

Collection

8 items • Updated Jun 20 • 6

Chocolatine🍫

Collection

DPO fine-tuned models Family, high performance • 11 items • Updated 6 days ago • 2

upvoted 2 collections 7 days ago

exl2 quants

Collection

14 items • Updated Jul 13 • 1

WoonaV1.2

Collection

4 items • Updated 7 days ago • 1

upvoted an article 7 days ago

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

May 24, 2023

• 79

upvoted 4 collections 7 days ago

Science LLM

Collection

8 items • Updated Apr 27 • 2

Small VLM

Collection

9 items • Updated Jul 5 • 2

My tools

Collection

Anything that might be useful • 8 items • Updated 7 days ago • 1

Picaro Magnum

Collection

2 items • Updated 7 days ago • 1

upvoted 2 collections 8 days ago

Synthetic texts

Collection

synthetic Japanese texts generated by llms (parquet化されていないデータがたくさんあります｡ dataフォルダ内のjsonlなどを直接読み込んでください • 29 items • Updated 8 days ago • 1

Picaro fixed for real

Collection

4 items • Updated 8 days ago • 1

upvoted a paper 9 days ago

VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges

Paper • 2409.01071 • Published 17 days ago • 26

John Smith PRO

AI & ML interests

Organizations

John6666's activity

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Introducing Community Tools

Fine-tuning Parler TTS on a Specific Language

Training Flux Locally on Mac

Fine-tuning a token classification model for legal data using Argilla and AutoTrain

Explaining the SDXL latent space

In-browser LLM app in pure Python: Gemini Nano + Gradio-Lite

Accelerate 1.0.0

"Diffusers Image Fill" guide

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA