Kalyan KS PRO

kalyan-ks

·

AI & ML interests

NLP (LLMs)

Recent Activity

liked a model about 13 hours ago

davanstrien/ultrabert-380m-curation

updated a model about 18 hours ago

kalyan-ks/ettin-17m-nemotron-pii

updated a model about 18 hours ago

kalyan-ks/ettin-32m-nemotron-pii

View all activity

Organizations

upvoted 3 articles 4 days ago

Article

Benchmarking Quantized Ammu-1.0 Off On Topic Guardrail Models: High-Throughput FP16 & FP8 on GPU (Part 2)

kalyan-ks

•

4 days ago

• 1

Article

DecisionFormer

FrontiersMind

•

8 days ago

• 9

Article

Introducing Lumma-Fev-v2

FrontiersMind

•

5 days ago

• 15

upvoted an article 6 days ago

Article

Benchmarking Quantized Ammu-1.0 Off On Topic Guardrail Models: Fast INT8 on CPU (Part 1)

kalyan-ks

•

6 days ago

• 1

upvoted an article 7 days ago

Article

Build specialized multimodal models with LFM3

LiquidAI

•

7 days ago

• 96

upvoted a collection 8 days ago

SauerkrautLM-MoEdernColBERT

Multilingual ColBERT retrievers on the MoEdernBERT architecture (1.5M, 27M, 115M) with GGUF and CoreML builds • 9 items • Updated 11 days ago • 13

upvoted a paper 15 days ago

Calibrated Typed Decisions for Entity, Relation, and Event Extraction

Paper • 2610.17113 • Published 23 days ago • 9

upvoted an article 16 days ago

Article

Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

ibm-granite

•

19 days ago

• 81

upvoted a collection 16 days ago

Indic-LLM-Eval-Suite

An open, community-driven evolving collection of benchmarks for comprehensive and reliable evaluation of LLMs across Indian Languages • 23 items • Updated 18 days ago • 1

upvoted 2 articles 17 days ago

Article

Ammu-1.0-OffOnTopic-Guardrail: Lightweight and Efficient Models for Off On Topic Guardrail Classification

kalyan-ks

•

17 days ago

• 1

Article

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

nvidia

•

19 days ago

• 51

upvoted 2 collections 18 days ago

Ammu-1.0 Off On Topic Guardrail

Collection of Ammu 1.0 Off On Topic Guardrail Models and Dataset • 9 items • Updated 10 days ago • 1

Lev

Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: 3 models + LevBench, training data and results. • 7 items • Updated 18 days ago • 5

upvoted a collection 19 days ago

Bonsai 2 Small

6 items • Updated 19 days ago • 51

upvoted an article 20 days ago

Article

Introducing Lumma-Fev-27B

FrontiersMind

•

20 days ago

• 24

upvoted a paper 20 days ago

LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them

Paper • 2610.02076 • Published about 1 month ago • 15

upvoted an article 22 days ago

Article

UIBK-Embedding-v1: A Dense and a Late-Interaction Retriever in One Model, One Index and One Search

abdoelsayed

•

22 days ago

• 14

upvoted a collection 24 days ago

Kev

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own • 6 items • Updated Oct 1 • 35

upvoted an article 24 days ago

Article

Ammu-1.0-FactCheck-Need: Lightweight and Efficient Models for Fact Check Need Classification

kalyan-ks

•

24 days ago

• 1

upvoted a changelog 25 days ago

Hugging Face Changelog

Decision Models on the Hub

25 days ago

• 228