Shahrukh Khan

shahrukhx01

·

https://github.com/shahrukhx01

AI & ML interests

NLP

Recent Activity

upvoted an article about 13 hours ago

SLMLogitsClassifier: How SLMs can be adapted to deliver efficient, robust and instruction-aligned classification in a single forward pass

liked a model about 13 hours ago

llm-semantic-router/mmbert-embed-32k-2d-matryoshka

liked a model 1 day ago

facebook/seamless-m4t-v2-large

View all activity

Organizations

upvoted an article about 13 hours ago

Article

SLMLogitsClassifier: How SLMs can be adapted to deliver efficient, robust and instruction-aligned classification in a single forward pass

UlrickBL

•

Dec 7, 2025

• 2

upvoted an article 17 days ago

Article

Beyond LoRA: Can you beat the most popular fine-tuning technique?

+2

BenjaminB, sayakpaul, hubnemo, kashif

•

18 days ago

• 71

upvoted a collection 19 days ago

Voxtral

Mistral AI Audio models. • 4 items • Updated Apr 14 • 13

upvoted a collection about 2 months ago

Boldt Models

Initial model release • 4 items • Updated May 4 • 2

upvoted 3 collections 2 months ago

Qwen-Scope

16 items • Updated May 14 • 75

GLiClass-Multilang

Multi-lingual zero-shot text classification models • 3 items • Updated Apr 30 • 8

MOSS-Audio

An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 9 items • Updated 24 days ago • 66

upvoted 3 collections 3 months ago

Qwen3.6

4 items • Updated Apr 22 • 427

Distil PII Redaction

A family of small language models (SLMs) specialized for policy-aware PII redaction that can run locally. • 7 items • Updated Feb 6 • 10

Gemma 4

15 items • Updated 25 days ago • 1.01k

upvoted 5 collections 4 months ago

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 75

DroPE

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding (https://www.arxiv.org/abs/2512.12167) • 1 item • Updated Jan 11 • 3

pplx-embed

Diffusion-Pretrained Dense and Contextual Embeddings • 10 items • Updated May 26 • 100

ColBERT-Zero 🐶

First large-scale fully pre-trained ColBERT model using only public data, outperforming GTE-ModernColBERT and GTE-ModernBERT • 10 items • Updated 11 days ago • 23

GLiClass-Instruct

Multi-task efficient zero-shot sequence classification models • 3 items • Updated Apr 30 • 5

upvoted a collection 5 months ago

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated Feb 27 • 41

upvoted an article 5 months ago

Article

Firecracker vs Docker: The Technical Boundary Between MicroVMs and Containers

agentbox-master

•

Nov 6, 2025

• 4

upvoted a collection 5 months ago

TranslateGemma

3 items • Updated Mar 12 • 245

upvoted an article 5 months ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

lightonai

•

Feb 12

• 58

upvoted a collection 5 months ago

NeuTTS Air

NeuTTS Air is a speech foundation model that runs on CPU in real-time, with instant voice cloning. • 3 items • Updated Jun 2 • 21