Kalyan KS's picture

Kalyan KS

kalyan-ks

·

kalyanks0611

AI & ML interests

NLP

Recent Activity

liked a model about 11 hours ago

google/embeddinggemma-300m

liked a model about 12 hours ago

Alibaba-NLP/gte-modernbert-base

reacted to danielhanchen's post with 🤗 1 day ago

Qwen releases 4 new Qwen3.5 Small models: 0.8B • 2B • 4B • 9B! Run Qwen3.5-0.8B, 2B and 4B on your phone. Run 9B on 6GB RAM. The vision reasoning LLMs perform better than models 4x their size. GGUFs to run: https://huggingface.co/collections/unsloth/qwen35 Guide: https://unsloth.ai/docs/models/qwen3.5

View all activity

Organizations

liked a model about 11 hours ago

google/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 2.04M • 1.5k

liked a model about 12 hours ago

Alibaba-NLP/gte-modernbert-base

Sentence Similarity • 0.1B • Updated Jul 4, 2025 • 139k • • 191

reacted to danielhanchen's post with 🤗 1 day ago

Post

5022

Qwen releases 4 new Qwen3.5 Small models: 0.8B • 2B • 4B • 9B!

Run Qwen3.5-0.8B, 2B and 4B on your phone. Run 9B on 6GB RAM.

The vision reasoning LLMs perform better than models 4x their size.

GGUFs to run: https://huggingface.co/collections/unsloth/qwen35

Guide: https://unsloth.ai/docs/models/qwen3.5

4 replies

·

liked a model 1 day ago

zeroentropy/zembed-1

Feature Extraction • 4B • Updated 2 days ago • 173 • 36

upvoted an article 2 days ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26, 2025

•

185

upvoted a collection 2 days ago

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 9 items • Updated Jan 14 • 450

upvoted a collection 3 days ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 3 days ago • 90

liked a model 4 days ago

Qwen/Qwen3.5-4B-Base

Image-Text-to-Text • 5B • Updated 4 days ago • 6.19k • 43

upvoted a collection 4 days ago

Qwen3.5

21 items • Updated 3 days ago • 971

upvoted an article 4 days ago

Article

Mixture of Experts (MoEs) in Transformers

+5

8 days ago

•

116

liked a model 6 days ago

BSC-LT/MrBERT

Fill-Mask • Updated 7 days ago • 167 • 3

liked a dataset 6 days ago

trl-lab/SQaLe-text-to-SQL-dataset

Viewer • Updated 3 days ago • 512k • 889 • 11

liked a dataset 7 days ago

dleemiller/FineCat-NLI

Viewer • Updated Oct 30, 2025 • 3.4M • 94 • 2

upvoted a collection 7 days ago

TinyLettuce

This Collection contains our small, Ettin-encoder (https://arxiv.org/abs/2507.11412) based models trained on synthetic and RagTruth data. • 6 items • Updated Aug 31, 2025 • 4

upvoted an article 8 days ago

Article

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

Oct 28, 2025

•

33

upvoted a collection 9 days ago

pplx-embed

Diffusion-Pretrained Dense and Contextual Embeddings • 7 items • Updated 8 days ago • 84

liked a model 10 days ago

LiquidAI/LFM2-24B-A2B

Text Generation • 24B • Updated 1 day ago • 13.7k • 264

upvoted an article 14 days ago

Article

ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models?

15 days ago

•

17

liked a model 15 days ago

jhu-clsp/ettin-encoder-17m

Fill-Mask • Updated Jul 16, 2025 • 15.2k • 14

upvoted a paper 15 days ago

RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models

Paper • 2401.00396 • Published Dec 31, 2023 • 6