Shahrukh Khan's picture

Shahrukh Khan

shahrukhx01

·

https://github.com/shahrukhx01

AI & ML interests

NLP

Organizations

shahrukhx01's activity

upvoted a collection 9 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 5 days ago • 160

upvoted a collection 10 days ago

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 3 days ago • 89

upvoted a collection 12 days ago

CompassJudger

4 items • Updated 25 days ago • 7

upvoted a collection 13 days ago

glm-4-voice

3 items • Updated 16 days ago • 2

upvoted a collection 18 days ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated 5 days ago • 86

upvoted a collection 22 days ago

LayerSkip

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated 14 days ago • 42

upvoted 3 collections about 1 month ago

Embedding Model Datasets

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 67 items • Updated Jul 3 • 74

MS MARCO Mined Triplets

These datasets contain MS MARCO Triplets gathered by mining hard negatives using various models. Each dataset has various subsets. • 14 items • Updated May 21 • 10

Parallel Sentences Datasets

These datasets all have "english" and "non_english" columns for numerous datasets. They can be used to make embedding models multilingual. • 14 items • Updated Oct 9 • 12

upvoted an article about 1 month ago

Article

Faster Assisted Generation with Dynamic Speculation

Oct 8

• 30

upvoted 9 collections about 1 month ago

em🍞ing series

crispy sentence embedding family • 5 items • Updated 26 days ago • 21

Nomic Embed

Open Source Long Context Text Embedders • 8 items • Updated Feb 14 • 16

ProLong

ProLong is a family of long-context models that are continued trained and supervised fine-tuned from Llama-3-8B, with a maximum context window of 512K • 7 items • Updated 18 days ago • 4

NuNerZero - Zero Shot NER

The best compact Zero-Shot NER models with MIT license • 4 items • Updated Jul 3 • 18

NuExtract

4 items • Updated 23 days ago • 9

Molmo

Artifacts for open multimodal language models. • 5 items • Updated Sep 26 • 269

Tower

Model weights and SFT data for Tower. • 10 items • Updated Oct 3 • 25

EuroLLM

2 items • Updated Aug 7 • 15

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 16 days ago • 451

upvoted a collection about 2 months ago

Strong German fp8 LLM's

Strong Large Language Models for the german language in fp8 format • 6 items • Updated Sep 24 • 3