John Gil Cubas

JohnRoger

·

JohnGilCubas

AI & ML interests

Natural language processing, computer social sciences

Recent Activity

liked a model 19 days ago

JohnRoger/VibeThinker-3B-Q8_0-GGUF

updated a model 19 days ago

JohnRoger/VibeThinker-3B-Q8_0-GGUF

published a model 19 days ago

JohnRoger/VibeThinker-3B-Q8_0-GGUF

View all activity

Organizations

upvoted a collection 19 days ago

Reasoning

137 items • Updated 3 days ago • 6

upvoted a collection 24 days ago

gemma-4-it-qat-abliterated

10 items • Updated 24 days ago • 6

upvoted a collection 25 days ago

DiffusionGemma

1 item • Updated 25 days ago • 56

upvoted a collection 26 days ago

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 107 items • Updated 7 days ago • 747

upvoted an article 26 days ago

Article

Introducing North Mini Code: Cohere’s First Model For Developers

CohereLabs

•

26 days ago

• 79

upvoted a collection 27 days ago

Gemma 4 QAT MTP

3 items • Updated 28 days ago • 1

upvoted a collection 29 days ago

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 21 days ago • 98

upvoted a collection about 1 month ago

Gemma 4 QAT Q4_0

19 items • Updated about 1 month ago • 140

upvoted a paper about 2 months ago

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Paper • 2605.13301 • Published May 13 • 165

upvoted 11 collections 2 months ago

GRaPE 2

The latest set of models in the GRaPE series • 8 items • Updated Apr 24 • 5

Ling 2.6

Ling-2.6 series is designed for real-world agents that require fast responses, strong execution, and high token efficiency, with several sized SKUs. • 6 items • Updated 14 days ago • 13

MathNet

3 items • Updated 20 days ago • 3

Huihui4-MoE-A4B

4 items • Updated Apr 27 • 3

Nemotron Math & Reasoning

Datasets for building models that excel at math reasoning, proofs, and quantitative problem-solving. Covers SFT, RL, and pretraining data. • 23 items • Updated 24 days ago • 11

Nemotron Supervised Fine-Tuning

SFT datasets covering math, code, chat, safety, agentic, VLM, multilingual, and specialized domains. • 44 items • Updated 24 days ago • 11

SimpleSD

Simple Self-Distillation • 3 items • Updated Apr 7 • 5

DeepSeek-V4

6 items • Updated 9 days ago • 716

MiMo-V2-Flash

MiMo-V2-Flash Series • 2 items • Updated Dec 17, 2025 • 30

Teacher Logits

Logits captured from large models to act as the teacher for distillation • 3 items • Updated Dec 15, 2025 • 12

Trinity-Large-Thinking

5 items • Updated Apr 10 • 32