John Smith's picture

John Smith PRO

John6666

·

John6666cat

AI & ML interests

None yet

Recent Activity

updated a collection 1 minute ago

LoRAs / Models (SDXL1.0, Pony, SD1.5, Flux, ...)

liked a model 2 minutes ago

deepghs/yolos

published a model 29 minutes ago

John6666/the-mind-games-ill-v10pocket-sdxl

View all activity

Organizations

John6666's activity

upvoted 2 collections about 12 hours ago

video-effects datasets

Smol datasets to emulate cool video effects like "squish", "dissolve", etc. Inspired by Pika effects. • 4 items • Updated 3 days ago • 1

video-effects

Fine-tunes of open video generation models like CogVideoX to emulate cool video effects like "squish", "dissolve", "cakeify", etc. Pika inspired. • 4 items • Updated 3 days ago • 3

upvoted an article about 12 hours ago

Article

Anthropic CEO: is DeepSeek-R1 a revolution in AI?

By

•

about 12 hours ago

• 2

upvoted a collection about 13 hours ago

Selene-1-Mini

4 items • Updated about 16 hours ago • 4

upvoted a collection about 18 hours ago

DeepSeek-R1 Distilled GGUF Models

LlamaEdge compatible quants for DeepSeek-R1 distilled models. • 6 items • Updated 1 day ago • 1

upvoted a collection about 19 hours ago

Eagle 2

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 8 days ago • 27

upvoted an article about 21 hours ago

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

By

•

1 day ago

• 19

upvoted an article 1 day ago

Article

🚀 Build a Qwen 2.5 VL API endpoint with Hugging Face spaces and Docker!

By

•

2 days ago

• 13

upvoted a collection 1 day ago

Qwen2.5-1M-abliterated

2 items • Updated 3 days ago • 1

upvoted an article 1 day ago

Article

Honesty, Open Source, and the Future of AI in Art: An Open Question

By

•

2 days ago

• 3

upvoted a collection 2 days ago

2025 January Papers 🧐

10 items • Updated 2 days ago • 4

upvoted 2 articles 2 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

3 days ago

• 467

Article

Fine-Tune Meta Llama 3.2-Vision-Instruct Multimodal LLM on Intel Accelerators

By

•

2 days ago

• 8

upvoted a paper 2 days ago

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published 5 days ago • 41

upvoted an article 3 days ago

Article

Welcome to Inference Providers on the Hub 🔥

3 days ago

• 172

upvoted 2 collections 3 days ago

Atlas Pro Preview

The version of Atlas is built on Atlas Flash to provide better reasoning and is perfect for tasks that require power and understanding from a model • 11 items • Updated 3 days ago • 2

Mimicore-Snake

New Year Merge Model, 'Human Response' • 3 items • Updated 3 days ago • 2

upvoted an article 3 days ago

Article

Reverse-engineering Custom-GPT prompts

By

•

3 days ago

• 5

upvoted 2 collections 3 days ago

My Spaces

Collection of SDXL Spaces Portfolio • 4 items • Updated 4 days ago • 2

Animagine XL

Collection of Animagine XL Models • 6 items • Updated 4 days ago • 3