kiran's picture

kiran

kira

·

ki6an

AI & ML interests

agi

Recent Activity

upvoted a collection 2 days ago

Nemotron-Post-Training-v3

upvoted an article about 1 month ago

Deriving the PPO Loss from First Principles

liked a model about 2 months ago

zai-org/GLM-4.7

View all activity

Organizations

upvoted a collection 2 days ago

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano v3. • 8 items • Updated 2 days ago • 62

upvoted an article about 1 month ago

Article

Deriving the PPO Loss from First Principles

Dec 25, 2025

•

35

upvoted a collection about 2 months ago

GLM-4.7

3 items • Updated 18 days ago • 62

upvoted an article about 2 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

+21

Jul 8, 2025

•

754

upvoted a collection 2 months ago

Olmo 3 Post-training

All artifacts for post-training Olmo 3. Datasets follow the model that resulted from training on them. • 32 items • Updated Dec 23, 2025 • 48

upvoted a collection 7 months ago

Tool Use Reasoning

A collection of tool use reasoning dataset in Hermes format • 5 items • Updated Jul 23, 2025 • 9

upvoted 3 papers 8 months ago

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published Jun 25, 2025 • 47

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

Paper • 2505.24726 • Published May 30, 2025 • 277

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Paper • 2505.24298 • Published May 30, 2025 • 28

upvoted a collection 10 months ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29, 2025 • 690

upvoted a paper about 1 year ago

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published Jan 23, 2025 • 48

upvoted 2 collections about 1 year ago

xLAM models

xLAM: A Family of Large Action Models to Empower AI Agent Systems: https://github.com/SalesforceAIResearch/xLAM • 22 items • Updated Nov 5, 2025 • 59

Qwen2.5-Coder

Code-specific model series based on Qwen2.5 • 40 items • Updated Dec 31, 2025 • 355

upvoted 4 collections over 1 year ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5, 2025 • 301

Mini Pretrain Datasets

9 items • Updated Jul 9, 2024 • 12

Useful Pretrain-Datasets

pretrain-datasets with (maybe) good quality • 21 items • Updated Mar 12, 2025 • 1

Yi-1.5 (2024/05)

10 items • Updated May 20, 2024 • 92

upvoted a collection almost 2 years ago

GPT-4 generated datasets

Collection of some GPT-4 generated datasets. It may be useful for those looking for the best-quality datasets to train competitive LLMs. • 18 items • Updated Apr 16, 2024 • 10

upvoted a paper almost 2 years ago

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12, 2024 • 66

upvoted a paper about 2 years ago

Tuning Language Models by Proxy

Paper • 2401.08565 • Published Jan 16, 2024 • 22