Oblx

OblxDev

9 1 7

AI & ML interests

None yet

Recent Activity

new activity 1 day ago

zai-org/GLM-5.2:Anyone tried this to run only on standard PC ram only?

liked a model 1 day ago

JBrightmanAI/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED

new activity 2 days ago

zai-org/GLM-5.2:All my documents are deleted :(

View all activity

Organizations

None yet

New activity in zai-org/GLM-5.2 1 day ago

Anyone tried this to run only on standard PC ram only?

#46 opened 5 days ago by

gemstonebro

liked a model 1 day ago

JBrightmanAI/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED

9B • Updated 2 days ago • 20 • 1

New activity in zai-org/GLM-5.2 2 days ago

All my documents are deleted :(

#48 opened 2 days ago by

jbourny

upvoted a paper 3 days ago

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Paper • 2607.07769 • Published 12 days ago • 8

New activity in zai-org/GLM-5.2 5 days ago

Dense 60-120B model

👍👀 7

#31 opened 20 days ago by

rtzurtz

New activity in zai-org/GLM-5 7 days ago

Is your model is using GEMINI?

#83 opened 7 days ago by

promaneh

New activity in zai-org/GLM-5.2 10 days ago

High Token Consumption and Cost Behavior in This Model

➕ 2

#33 opened 18 days ago by

mehranpng

liked 2 models 10 days ago

nvidia/Kimi-K2.7-Code-DFlash

Text Generation • 3B • Updated 11 days ago • 1.32k • 9

Jackrong/Qwopus3.5-27B-v3-GGUF

Image-Text-to-Text • 27B • Updated 11 days ago • 3.23k • 352

reacted to sergiopaniego's post with ❤️ 10 days ago

Post

7631

Frontier models use distillation as a step of their post-training pipelines.

In 2026 it has three jobs: compress a big model into a small one, merge RL experts into a single model, and let a model teach itself.

I wrote up which frontier models use each one and how: https://huggingface.co/blog/sergiopaniego/distillation-2026

It pairs with Class 2 of the Training an Agent series Ben and I are doing, where we teach these techniques hands-on with TRL!