Ben Kelly's picture

In a Training Loop 🔄

Ben Kelly PRO

YellowjacketGames

·

manacasterben

AI & ML interests

None yet

Recent Activity

updated a dataset about 6 hours ago

YellowjacketGames/orc-assist-icons

replied to danielhanchen's post about 6 hours ago

Qwen releases Qwen3-Coder-Next! 💜 Run the locally on 46GB RAM or less. Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20× more active parameters. GGUF: https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF Guide: https://unsloth.ai/docs/models/qwen3-coder-next

updated a collection about 14 hours ago

[papers] Distillation

View all activity

Organizations

updated a dataset about 6 hours ago

YellowjacketGames/orc-assist-icons

Viewer • Updated about 6 hours ago • 24 • 17

replied to danielhanchen's post about 6 hours ago

fits almst perfectly into an a6000!

updated a collection about 14 hours ago

[papers] Distillation

12 items • Updated about 14 hours ago • 2

upvoted a paper about 14 hours ago

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Paper • 2503.07067 • Published Mar 10, 2025 • 32

updated a collection about 14 hours ago

[papers] Distillation

12 items • Updated about 14 hours ago • 2

upvoted a paper about 14 hours ago

PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters

Paper • 2504.08791 • Published Apr 7, 2025 • 139

updated a collection about 17 hours ago

[mixed] Image Generation Stack

The stuff we actually use, pruned on an ongoing basis. • 11 items • Updated about 17 hours ago • 1

upvoted a paper about 17 hours ago

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Paper • 2602.02437 • Published 1 day ago • 71

New activity in YellowjacketGames/orc-assist-icons 1 day ago

[bot] Conversion to Parquet

#1 opened 1 day ago by

parquet-converter

updated a collection 1 day ago

[mixed] ORCAssist "Work's Done!"

17 items • Updated 1 day ago • 1

published a dataset 1 day ago

YellowjacketGames/orc-assist-icons

Viewer • Updated about 6 hours ago • 24 • 17

updated a collection 1 day ago

[papers] Distillation

12 items • Updated about 14 hours ago • 2

upvoted a paper 1 day ago

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

Paper • 2601.22146 • Published 5 days ago • 8

updated a collection 1 day ago

[papers] Distillation

12 items • Updated about 14 hours ago • 2

upvoted a paper 1 day ago

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Paper • 2601.18734 • Published 8 days ago • 2

updated a collection 1 day ago

[papers] Distillation

12 items • Updated about 14 hours ago • 2

upvoted a paper 1 day ago

Self-Improving Pretraining: using post-trained models to pretrain better models

Paper • 2601.21343 • Published 6 days ago • 14

commented a paper 1 day ago

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

Paper • 2512.03324 • Published Dec 3, 2025 • 1 •

updated a collection 1 day ago

[papers] Distillation

12 items • Updated about 14 hours ago • 2

upvoted a paper 1 day ago

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

Paper • 2512.03324 • Published Dec 3, 2025 • 1