Research directly related to Chess technology.
Ben Kelly PRO
YellowjacketGames
AI & ML interests
None yet
Recent Activity
updated
a collection
about 3 hours ago
[mixed] ORCAssist "Work's Done!"
updated
a dataset
about 3 hours ago
YellowjacketGames/orc-assist-icons
published
a dataset
about 3 hours ago
YellowjacketGames/orc-assist-icons
Organizations
[models] RTX a6000 48gb
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
[models] CPU-Offload &/|| A6000x2
TPS can be as low as 1.0, seriously. its SLOW.
-
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 103k • 193 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 3.01k • 193 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-to-Text • 401B • Updated • 5.08k • 43 -
unsloth/MiniMax-M2.1-GGUF
Text Generation • 229B • Updated • 120k • 167
[models] iGPU-Capable < 512mb
hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.
[mixed] ORCAssist "Work's Done!"
[mixed] Scientific Method
[papers] RAG$ to Riche$
-
UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation
Paper • 2504.08761 • Published • 7 -
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 112 -
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal
Paper • 2601.18081 • Published • 7
[papers] Film & Cinema
[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 • 3 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 52 -
Zero-Overhead Introspection for Adaptive Test-Time Compute
Paper • 2512.01457 • Published • 2 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 16
[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.
[models] Sub-1gb for Edge
Toaster Tier but not iGPU
[models] non-EN specialists
Emphasis on Portuguese, Spanish, Vietnamese, Hebrew
[mixed] Image Generation Stack
The stuff we actually use, pruned on an ongoing basis.
[papers] Distillation
-
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Paper • 2601.14249 • Published • 9 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19 -
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
Paper • 2601.07251 • Published • 11 -
GameTalk: Training LLMs for Strategic Conversation
Paper • 2601.16276 • Published • 12
[papers] Sports Tech
[data] What a Dump!
Seriously, look at the size of these dumps! They're a huge pile of data, dumped on your doorstep!
[mixed] Chess x AI
Research directly related to Chess technology.
[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 • 3 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 52 -
Zero-Overhead Introspection for Adaptive Test-Time Compute
Paper • 2512.01457 • Published • 2 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 16
[models] RTX a6000 48gb
Models that run well on a *standalone* RTX a6000's 48gb of VRAM.
[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.
[models] CPU-Offload &/|| A6000x2
TPS can be as low as 1.0, seriously. its SLOW.
-
unsloth/GLM-4.7-GGUF
Text Generation • 358B • Updated • 103k • 193 -
unsloth/DeepSeek-R1-0528-GGUF
Text Generation • 671B • Updated • 3.01k • 193 -
unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF
Image-to-Text • 401B • Updated • 5.08k • 43 -
unsloth/MiniMax-M2.1-GGUF
Text Generation • 229B • Updated • 120k • 167
[models] Sub-1gb for Edge
Toaster Tier but not iGPU
[models] iGPU-Capable < 512mb
hey, you gotta try. any precision acceptable here, QA check the actual result quality. at your own risk, fool.
[models] non-EN specialists
Emphasis on Portuguese, Spanish, Vietnamese, Hebrew
[mixed] ORCAssist "Work's Done!"
[mixed] Image Generation Stack
The stuff we actually use, pruned on an ongoing basis.
[mixed] Scientific Method
[papers] Distillation
-
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Paper • 2601.14249 • Published • 9 -
Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
Paper • 2402.07033 • Published • 19 -
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
Paper • 2601.07251 • Published • 11 -
GameTalk: Training LLMs for Strategic Conversation
Paper • 2601.16276 • Published • 12
[papers] RAG$ to Riche$
-
UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation
Paper • 2504.08761 • Published • 7 -
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 112 -
DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal
Paper • 2601.18081 • Published • 7
[papers] Sports Tech
[papers] Film & Cinema
[data] What a Dump!
Seriously, look at the size of these dumps! They're a huge pile of data, dumped on your doorstep!