Shahrukh Khan's picture

Shahrukh Khan

shahrukhx01

·

https://github.com/shahrukhx01

AI & ML interests

NLP

Recent Activity

upvoted a collection 3 days ago

liked a model 5 days ago

nvidia/personaplex-7b-v1

upvoted a collection 10 days ago

View all activity

Organizations

upvoted a collection 3 days ago

Qwen3-TTS

7 items • Updated 4 days ago • 216

upvoted a collection 10 days ago

Falcon-H1-Tiny

A series of extremely small, yet powerful language models redefining capabilities at small scale • 22 items • Updated 11 days ago • 27

upvoted a collection about 2 months ago

VibeVoice

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 9 items • Updated 5 days ago • 201

upvoted an article about 2 months ago

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

311

upvoted a collection 2 months ago

Tarka Embed V1

Efficient DFKD embeddings for language understanding • 5 items • Updated Dec 17, 2025 • 6

upvoted a collection 4 months ago

GLiNER-PII

PII detection models developed in collaboration with Wordcab • 5 items • Updated Sep 24, 2025 • 21

upvoted an article 4 months ago

Article

🕳️ Attention Sinks in LLMs for endless fluency

Oct 9, 2023

•

34

upvoted 2 collections 4 months ago

Qwen3-Omni

6 items • Updated 26 days ago • 181

MobileLLM-R1

MobileLLM-R1, a series of sub-billion parameter reasoning models • 10 items • Updated Nov 21, 2025 • 27

upvoted a collection 5 months ago

Gemma 3 Release

28 items • Updated Aug 11, 2025 • 597

upvoted a collection 6 months ago

Encoders vs Decoders: the Ettin Suite

A collection of SOTA, open-data, paired encoder-only and decoder only models ranging from 17M params to 1B. See the paper at https://arxiv.org/abs/250 • 32 items • Updated Jul 16, 2025 • 25

upvoted a collection 7 months ago

GLiNER-X

The Multilingual Named Entity Recognition (NER) model which is capable of identifying any entity type. • 6 items • Updated Jun 24, 2025 • 21

upvoted an article 7 months ago

Article

Transformers backend integration in SGLang

+3

Jun 23, 2025

•

54

upvoted 3 collections 8 months ago

Qwen3-Reranker

3 items • Updated 26 days ago • 64

Qwen3-Embedding

6 items • Updated 26 days ago • 145

Falcon-H1

Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned). • 39 items • Updated 17 days ago • 59

upvoted an article 8 months ago

Article

🥬 LettuceDetect Goes Multilingual: Fine-tuning EuroBERT on Synthetic Translations

May 19, 2025

•

9

upvoted an article 9 months ago

Article

You could have designed state of the art positional encoding

Nov 25, 2024

•

442

upvoted 2 collections 9 months ago

Deepseek Papers

Deepseek papers collection • 28 items • Updated about 10 hours ago • 316

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10, 2025 • 215