Zubin's picture

Zubin

zubinb

·

AI & ML interests

None yet

Recent Activity

liked a model about 10 hours ago

mlx-community/embeddinggemma-300m-4bit

liked a model about 13 hours ago

deepreinforce-ai/Ornith-1.0-9B

upvoted a collection about 13 hours ago

View all activity

Organizations

None yet

upvoted a collection about 13 hours ago

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 2 days ago • 232

upvoted a collection 4 days ago

openPangu

A series of openPangu LLMs with different parameters. • 8 items • Updated Mar 2 • 5

upvoted 4 collections 6 days ago

Good RP Models

List of models for extremely dark NSFW roleplay that I tested. The best models will be on top of the list (mostly). • 29 items • Updated May 26 • 121

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 121 items • Updated 18 days ago • 115

Jamba Reasoning 3B

AI21's top-performing reasoning model that packs leading scores on intelligence benchmarks and highly-efficient processing into a compact 3B build • 2 items • Updated Oct 8, 2025 • 9

MeroMero

Gemma 4 Series • 2 items • Updated May 2 • 8

upvoted a collection 8 days ago

Macaron-V1

2 items • Updated 22 days ago • 7

upvoted a paper 9 days ago

CEO-Bench: Can Agents Play the Long Game?

Paper • 2606.18543 • Published 13 days ago • 8

upvoted a paper 12 days ago

Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion

Paper • 2606.15236 • Published 13 days ago • 21

upvoted 2 papers 13 days ago

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2606.15007 • Published 17 days ago • 16

LLM Agents Can See Code Repositories

Paper • 2606.14061 • Published 17 days ago • 20

upvoted a collection 15 days ago

EmbeddingGemma

3 items • Updated Mar 12 • 121

upvoted a collection 17 days ago

Kimi K2.5

Moonshot's most powerful model • 4 items • Updated 17 days ago • 76

upvoted a paper 17 days ago

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Paper • 2606.12344 • Published 19 days ago • 70

upvoted 2 articles 17 days ago

Article

Memory Is Evidence, Not Instruction: NZFC-GRAM v1.2.4 and the Case for Governed AI Memory

SingularityPrinciple

•

20 days ago

• 2

Article

DiffusionGemma-26B-A4B-it-Infinite-Context: External Evidence Memory for the Diffusion LLM Era

SingularityPrinciple

•

18 days ago

• 1

upvoted 2 collections 18 days ago

DiffusionGemma

8 items • Updated 19 days ago • 16

DiffusionGemma

1 item • Updated 19 days ago • 54

upvoted a collection 19 days ago

Nex-N2

3 items • Updated 18 days ago • 21

upvoted an article 19 days ago

Article

Vision Tokens vs Text Tokens: Understanding the 10× Compression

onekq

•

Oct 22, 2025

• 7