🔄 In a Training Loop

15 93 63

Ben Kelly PRO

YellowjacketGames

julien-c's profile picture

Fishtiks's profile picture

flaviocb's profile picture

manacasterben

AI & ML interests

None yet

Recent Activity

new activity 3 days ago

UofTCSSLab/Maia3-79M:why AGPL?

upvoted a collection 3 days ago

Maia3

liked a model 3 days ago

UofTCSSLab/Maia3-79M

View all activity

Organizations

YellowjacketGames 's collections 18

[Models] YJ Audio Stack

Curated

fishaudio/s2-pro

Text-to-Speech • 5B • Updated Mar 11 • 358k • 1.05k
CohereLabs/cohere-transcribe-03-2026

Automatic Speech Recognition • 2B • Updated 13 days ago • 735k • 1.01k
Soul-AILab/SoulX-Singer

Text-to-Speech • Updated Mar 13 • 806 • 162
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • 2B • Updated Jan 29 • 2.15M • 1.63k

[mixed] Chess x AI

Research directly related to Chess technology.

Lichess/standard-chess-games

Viewer • Updated Oct 16, 2025 • 7.14B • 15.7k • 71
Lichess/tournament-chess-games

Viewer • Updated Dec 9, 2025 • 931k • 2.8k • 7
Lichess/three-check-chess-games

Viewer • Updated Oct 16, 2025 • 9.41M • 78 • 2
Lichess/chess-puzzles

Viewer • Updated 12 days ago • 6.01M • 3.98k • 29

[models] RTX a6000 48gb

Models that run well on a *standalone* RTX a6000's 48gb of VRAM.

unsloth/Qwen-Image-Edit-2511-GGUF

Image-to-Image • 20B • Updated Jan 8 • 239k • 512
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF

24B • Updated Dec 15, 2025 • 44.7k • 149
zai-org/GLM-Image

Text-to-Image • Updated Jan 15 • 44.1k • • 1.08k
nvidia/personaplex-7b-v1

Audio-to-Audio • 8B • Updated Mar 2 • 345k • 2.57k

[models] CPU-Offload &/|| A6000x2

TPS can be as low as 1.0, seriously. its SLOW.

unsloth/GLM-4.7-GGUF

Text Generation • 358B • Updated Dec 27, 2025 • 10.3k • 219
unsloth/DeepSeek-R1-0528-GGUF

Text Generation • 671B • Updated Jun 15, 2025 • 5.65k • 199
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF

Image-Text-to-Text • 401B • Updated Jun 18, 2025 • 11k • 49
unsloth/MiniMax-M2.1-GGUF

Text Generation • 229B • Updated Feb 14 • 5.27k • 194

[models] iGPU-Capable < 512mb

hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.

unsloth/LFM2.5-1.2B-Thinking-GGUF

Text Generation • 1B • Updated Jan 21 • 1.59k • 13

[models] Image Generation Stack

The stuff we actually use, pruned on an ongoing basis.

black-forest-labs/FLUX.2-dev

Image-to-Image • Updated Feb 17 • 303k • • 1.82k
unsloth/Qwen-Image-Edit-2511-GGUF

Image-to-Image • 20B • Updated Jan 8 • 239k • 512
zai-org/GLM-Image

Text-to-Image • Updated Jan 15 • 44.1k • • 1.08k
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA

Image-to-Image • Updated Jan 7 • 66.3k • • 1.43k

[mixed] Scientific Method

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Paper • 2601.20833 • Published Jan 28 • 183

[papers] RAG$ to Riche$

UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation

Paper • 2504.08761 • Published Mar 31, 2025 • 7
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling

Paper • 2512.23959 • Published Dec 30, 2025 • 111
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Paper • 2601.18081 • Published Jan 26 • 8
nvidia/nemotron-colembed-vl-8b-v2

Visual Document Retrieval • 9B • Updated Feb 21 • 13.6k • 47

[papers] Image & Video

The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

Paper • 2601.17737 • Published Jan 25 • 56
Advancing Open-source World Models

Paper • 2601.20540 • Published Jan 28 • 135
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

Paper • 2601.15369 • Published Jan 21 • 22
Video-As-Prompt: Unified Semantic Control for Video Generation

Paper • 2510.20888 • Published Oct 23, 2025 • 50

OpenClaw Fun!

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)

Paper • 2602.14364 • Published Feb 16 • 25
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

Paper • 2602.14299 • Published Feb 15 • 27
AIDev: Studying AI Coding Agents on GitHub

Paper • 2602.09185 • Published Feb 9 • 3
bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF

Text Generation • 32B • Updated Mar 22 • 9.26k • 37

[papers] Gameplay Optimization

Research papers that may contribute to a broader approach to teaching machines how to play complex strategy games beyond just Chess.

OptiMind: Teaching LLMs to Think Like Optimization Experts

Paper • 2509.22979 • Published Sep 26, 2025 • 4
LFM2 Technical Report

Paper • 2511.23404 • Published Nov 28, 2025 • 61
Zero-Overhead Introspection for Adaptive Test-Time Compute

Paper • 2512.01457 • Published Dec 1, 2025 • 3
Confidence Estimation for LLMs in Multi-turn Interactions

Paper • 2601.02179 • Published Jan 5 • 17

[models] GTX 1660 Super 6gb

The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize.

MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF

Text Generation • 8B • Updated Dec 6, 2025 • 64.6k • 6
unsloth/Qwen3-4B-Instruct-2507-GGUF

4B • Updated Aug 20, 2025 • 80.2k • 181
unsloth/SmolLM3-3B-128K-GGUF

3B • Updated Jul 8, 2025 • 2.88k • 42
unsloth/Ministral-3-3B-Reasoning-2512-GGUF

3B • Updated Dec 4, 2025 • 6.66k • 20

[models] Sub-1gb for Edge

Toaster Tier but not iGPU

lmstudio-community/LFM2.5-1.2B-Thinking-GGUF

1B • Updated Jan 20 • 1.32k • 2
unsloth/SmolLM3-3B-128K-GGUF

3B • Updated Jul 8, 2025 • 2.88k • 42

[models] non-EN specialists

Emphasis on Portuguese, Spanish, Vietnamese, Hebrew

lucifrrrrrrrrrr/vn-geography-8b

8B • Updated Jan 25 • 49 • 2

[mixed] ORCAssist "Work's Done!"

YellowjacketGames/orc-assist-icons

Viewer • Updated May 21 • 48 • 66 • 1
nvidia/Nemotron-Orchestrator-8B

Text Generation • 8B • Updated Dec 2, 2025 • 4.97k • • 585
allenai/SERA-8B-GA

8B • Updated Feb 3 • 14 • 15
GAIR/daVinci-Dev-72B

Text Generation • 73B • Updated 15 days ago • 31 • 8

[papers] Distillation

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Paper • 2601.14249 • Published Jan 20 • 14
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Paper • 2402.07033 • Published Feb 10, 2024 • 19
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences

Paper • 2601.07251 • Published Jan 12 • 11
GameTalk: Training LLMs for Strategic Conversation

Paper • 2601.16276 • Published Jan 22 • 14

[papers] Sports Tech

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Paper • 2601.14255 • Published Jan 20 • 15
Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Paper • 2601.14253 • Published Jan 20 • 10
Think3D: Thinking with Space for Spatial Reasoning

Paper • 2601.13029 • Published Jan 19 • 48
netflix/void-model

Video-to-Video • Updated Apr 6 • 946

[data] What a Dump!

Seriously, look at the size of these dumps! They're a huge pile of data, dumped on your doorstep!

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5, 2025 • 62
Lichess/standard-chess-games

Viewer • Updated Oct 16, 2025 • 7.14B • 15.7k • 71
Lichess/chess-puzzles

Viewer • Updated 12 days ago • 6.01M • 3.98k • 29
nvidia/SAGE-10k

Updated Feb 11 • 65.1k • 77

[Models] YJ Audio Stack

Curated

fishaudio/s2-pro

Text-to-Speech • 5B • Updated Mar 11 • 358k • 1.05k
CohereLabs/cohere-transcribe-03-2026

Automatic Speech Recognition • 2B • Updated 13 days ago • 735k • 1.01k
Soul-AILab/SoulX-Singer

Text-to-Speech • Updated Mar 13 • 806 • 162
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • 2B • Updated Jan 29 • 2.15M • 1.63k

OpenClaw Fun!

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)

Paper • 2602.14364 • Published Feb 16 • 25
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

Paper • 2602.14299 • Published Feb 15 • 27
AIDev: Studying AI Coding Agents on GitHub

Paper • 2602.09185 • Published Feb 9 • 3
bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF

Text Generation • 32B • Updated Mar 22 • 9.26k • 37

[mixed] Chess x AI

Research directly related to Chess technology.

Lichess/standard-chess-games

Viewer • Updated Oct 16, 2025 • 7.14B • 15.7k • 71
Lichess/tournament-chess-games

Viewer • Updated Dec 9, 2025 • 931k • 2.8k • 7
Lichess/three-check-chess-games

Viewer • Updated Oct 16, 2025 • 9.41M • 78 • 2
Lichess/chess-puzzles

Viewer • Updated 12 days ago • 6.01M • 3.98k • 29

[papers] Gameplay Optimization

Research papers that may contribute to a broader approach to teaching machines how to play complex strategy games beyond just Chess.

OptiMind: Teaching LLMs to Think Like Optimization Experts

Paper • 2509.22979 • Published Sep 26, 2025 • 4
LFM2 Technical Report

Paper • 2511.23404 • Published Nov 28, 2025 • 61
Zero-Overhead Introspection for Adaptive Test-Time Compute

Paper • 2512.01457 • Published Dec 1, 2025 • 3
Confidence Estimation for LLMs in Multi-turn Interactions

Paper • 2601.02179 • Published Jan 5 • 17

[models] RTX a6000 48gb

Models that run well on a *standalone* RTX a6000's 48gb of VRAM.

unsloth/Qwen-Image-Edit-2511-GGUF

Image-to-Image • 20B • Updated Jan 8 • 239k • 512
unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF

24B • Updated Dec 15, 2025 • 44.7k • 149
zai-org/GLM-Image

Text-to-Image • Updated Jan 15 • 44.1k • • 1.08k
nvidia/personaplex-7b-v1

Audio-to-Audio • 8B • Updated Mar 2 • 345k • 2.57k

[models] GTX 1660 Super 6gb

The best little card under 100 euros. Full Precision vs Quants not benchmarked. This card is so much better at running inference than you realize.

MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF

Text Generation • 8B • Updated Dec 6, 2025 • 64.6k • 6
unsloth/Qwen3-4B-Instruct-2507-GGUF

4B • Updated Aug 20, 2025 • 80.2k • 181
unsloth/SmolLM3-3B-128K-GGUF

3B • Updated Jul 8, 2025 • 2.88k • 42
unsloth/Ministral-3-3B-Reasoning-2512-GGUF

3B • Updated Dec 4, 2025 • 6.66k • 20

[models] CPU-Offload &/|| A6000x2

TPS can be as low as 1.0, seriously. its SLOW.

unsloth/GLM-4.7-GGUF

Text Generation • 358B • Updated Dec 27, 2025 • 10.3k • 219
unsloth/DeepSeek-R1-0528-GGUF

Text Generation • 671B • Updated Jun 15, 2025 • 5.65k • 199
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF

Image-Text-to-Text • 401B • Updated Jun 18, 2025 • 11k • 49
unsloth/MiniMax-M2.1-GGUF

Text Generation • 229B • Updated Feb 14 • 5.27k • 194

[models] Sub-1gb for Edge

Toaster Tier but not iGPU

lmstudio-community/LFM2.5-1.2B-Thinking-GGUF

1B • Updated Jan 20 • 1.32k • 2
unsloth/SmolLM3-3B-128K-GGUF

3B • Updated Jul 8, 2025 • 2.88k • 42

[models] iGPU-Capable < 512mb

hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.

unsloth/LFM2.5-1.2B-Thinking-GGUF

Text Generation • 1B • Updated Jan 21 • 1.59k • 13

[models] non-EN specialists

Emphasis on Portuguese, Spanish, Vietnamese, Hebrew

lucifrrrrrrrrrr/vn-geography-8b

8B • Updated Jan 25 • 49 • 2

[models] Image Generation Stack

The stuff we actually use, pruned on an ongoing basis.

black-forest-labs/FLUX.2-dev

Image-to-Image • Updated Feb 17 • 303k • • 1.82k
unsloth/Qwen-Image-Edit-2511-GGUF

Image-to-Image • 20B • Updated Jan 8 • 239k • 512
zai-org/GLM-Image

Text-to-Image • Updated Jan 15 • 44.1k • • 1.08k
fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA

Image-to-Image • Updated Jan 7 • 66.3k • • 1.43k

[mixed] ORCAssist "Work's Done!"

YellowjacketGames/orc-assist-icons

Viewer • Updated May 21 • 48 • 66 • 1
nvidia/Nemotron-Orchestrator-8B

Text Generation • 8B • Updated Dec 2, 2025 • 4.97k • • 585
allenai/SERA-8B-GA

8B • Updated Feb 3 • 14 • 15
GAIR/daVinci-Dev-72B

Text Generation • 73B • Updated 15 days ago • 31 • 8

[mixed] Scientific Method

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Paper • 2601.20833 • Published Jan 28 • 183

[papers] Distillation

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Paper • 2601.14249 • Published Jan 20 • 14
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Paper • 2402.07033 • Published Feb 10, 2024 • 19
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences

Paper • 2601.07251 • Published Jan 12 • 11
GameTalk: Training LLMs for Strategic Conversation

Paper • 2601.16276 • Published Jan 22 • 14

[papers] RAG$ to Riche$

UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation

Paper • 2504.08761 • Published Mar 31, 2025 • 7
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling

Paper • 2512.23959 • Published Dec 30, 2025 • 111
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Paper • 2601.18081 • Published Jan 26 • 8
nvidia/nemotron-colembed-vl-8b-v2

Visual Document Retrieval • 9B • Updated Feb 21 • 13.6k • 47

[papers] Sports Tech

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Paper • 2601.14255 • Published Jan 20 • 15
Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Paper • 2601.14253 • Published Jan 20 • 10
Think3D: Thinking with Space for Spatial Reasoning

Paper • 2601.13029 • Published Jan 19 • 48
netflix/void-model

Video-to-Video • Updated Apr 6 • 946

[papers] Image & Video

The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

Paper • 2601.17737 • Published Jan 25 • 56
Advancing Open-source World Models

Paper • 2601.20540 • Published Jan 28 • 135
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

Paper • 2601.15369 • Published Jan 21 • 22
Video-As-Prompt: Unified Semantic Control for Video Generation

Paper • 2510.20888 • Published Oct 23, 2025 • 50

[data] What a Dump!

Seriously, look at the size of these dumps! They're a huge pile of data, dumped on your doorstep!

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published Jun 5, 2025 • 62
Lichess/standard-chess-games

Viewer • Updated Oct 16, 2025 • 7.14B • 15.7k • 71
Lichess/chess-puzzles

Viewer • Updated 12 days ago • 6.01M • 3.98k • 29
nvidia/SAGE-10k

Updated Feb 11 • 65.1k • 77