charlie

MC7ever

·

nutter77-fossmc

AI & ML interests

new emerging techniques, converting to mamba3, bootleg operations, fine tunes, inference and training all on shitty hardware

Recent Activity

liked a model about 7 hours ago

Takenoko12345678/Spark-X2.5-4B-Japanese-Pitcher

liked a dataset about 7 hours ago

OysterCoreAI/SFT-General-Japanese-60K

liked a model about 7 hours ago

Takenoko12345678/Spark-X2.5-4B-Japanese

View all activity

Organizations

upvoted a paper 13 days ago

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

Paper • 2605.30076 • Published May 28 • 26

upvoted 2 papers 14 days ago

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 38

Closed-Form Spectral Regularization for Multi-Task Model Merging

Paper • 2606.07289 • Published Jun 5 • 2

upvoted a paper 22 days ago

HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs

Paper • 2509.23967 • Published Sep 28, 2025 • 5

upvoted 9 collections about 2 months ago

Nemotron-Personas

A collection of multilingual, region-specific synthetic persona datasets that support sovereign AI development across many countries and regions. • 10 items • Updated Aug 11 • 76

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated Aug 11 • 203

Nemotron Agentic & Tool-Use

Datasets for building models capable of function calling, multi-step agentic tasks, terminal use, and SWE workflows. • 11 items • Updated Aug 11 • 24

Nemotron-Pre-Training-Datasets

Large scale pre-training datasets used in the Nemotron family of models. • 15 items • Updated Aug 11 • 195

Nemotron Reward Modeling

Human preference data, reward model training sets, and generative reward modeling data for training Nemotron reward models. • 6 items • Updated Aug 11 • 5

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 Aug 11 • 16

Nemotron Chat & Instruction Following

Datasets for building helpful, multi-turn, instruction-following conversational models across single and multi-turn settings. • 19 items • Updated Aug 11 • 10

Nemotron Code & SWE

Datasets for building models that write, debug, and reason about code. Covers competitive programming, software engineering, and code pretraining. • 14 items • Updated Aug 11 • 9

Nemotron Supervised Fine-Tuning

SFT datasets covering math, code, chat, safety, agentic, VLM, multilingual, and specialized domains. • 44 items • Updated Aug 11 • 22

upvoted 2 articles 2 months ago

Article

Security incident disclosure — July 2026

system

•

Jul 16

• 799

Article

Heretic Grimoire

VINAY-UMRETHE

•

Jun 30

• 6