John Smith's picture

In a Training Loop 🔄

John Smith PRO

John6666

·

John6666cat

AI & ML interests

None yet

Recent Activity

liked a model about 7 hours ago

wallacebf/AurIA-G3-v1

liked a model about 7 hours ago

mradermacher/AurIA-G3-v1-GGUF

liked a model about 7 hours ago

Ratnesh123/antigravity-qwen2.5-3b

View all activity

Organizations

upvoted a collection about 8 hours ago

RoboBrain2.5

RoboBrain 2.5: Depth in Sight, Time in Mind. • 4 items • Updated about 9 hours ago • 7

upvoted an article 2 days ago

Article

Mixture of Experts (MoEs) in Transformers

+5

3 days ago

•

91

upvoted a changelog 2 days ago

Changelog

Public Storage Add-ons

2 days ago

• 49

upvoted an article 5 days ago

Article

Do Bubbles Form When Tens of Thousands of AIs Simulate Capitalism?

5 days ago

•

16

upvoted a collection 5 days ago

Qwen3 Voice Embedding

Standalone ECAPA-TDNN x-vector speaker encoders extracted from Qwen3-TTS. 1024-dim (0.6B) and 2048-dim (1.7B). • 4 items • Updated 1 day ago • 26

upvoted an article 7 days ago

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

+4

9 days ago

•

469

upvoted a collection 8 days ago

The Bestiary

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16, 2025 • 99

upvoted 2 articles 9 days ago

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

+4

9 days ago

•

76

Article

How We Learned to Talk to Machines

9 days ago

•

3

upvoted a collection 10 days ago

Custom HTML Component

With Gradio 6 you can now create custom components using the gr.HTML component. This is a collection of some apps built with this cool new component. • 11 items • Updated 2 days ago • 5

upvoted an article 10 days ago

Article

One-Shot Any Web App with Gradio's gr.HTML

+1

11 days ago

•

20

upvoted 2 collections 10 days ago

llava

2 items • Updated Feb 26, 2024 • 1

PRIME

PRIME data & models • 4 items • Updated 21 days ago • 3

upvoted 5 collections 11 days ago

OPRM

8 items • Updated 19 days ago • 2

Gemma 3 - Reasoning/Thinking Models (incl uncensored)

Fine tunes (most uncensored) of Gemma3s to add reasoning/thinking. Increases output and image processing quality and general model metrics. • 26 items • Updated about 15 hours ago • 14

Unredacted MAX - VL [GGUF]

multi-stage trained continual "abliteration" approach for the qwen3-vl series models (GGUF) • 4 items • Updated 13 days ago • 4

Unredacted MAX - VL

multi-stage trained continual "abliteration" approach for the qwen3-vl series models • 4 items • Updated 12 days ago • 4

Unredacted MAX - VL [FP8]

[FP8_DYNAMIC] multi-stage trained continual "abliteration" approach for the qwen3-vl series models • 10 items • Updated 4 days ago • 2

upvoted an article 13 days ago

Article

Custom Kernels for All from Codex and Claude

+2

16 days ago

•

64

upvoted an article 14 days ago

Article

Forge: Scalable Agent RL Framework and Algorithm

16 days ago

•

127