akashicmarga (Akash Singh)

upvoted a collection 2 days ago

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 6 items • Updated 3 days ago • 78

upvoted a collection about 1 month ago

Moshi v0.1 Release

Collection

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18 • 212

upvoted a paper 7 months ago

Octopus v2: On-device language model for super agent

Paper • 2404.01744 • Published Apr 2 • 57

upvoted 2 papers 9 months ago

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Paper • 2402.07033 • Published Feb 10 • 16

StarCoder: may the source be with you!

Paper • 2305.06161 • Published May 9, 2023 • 29

upvoted a paper 10 months ago

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Paper • 2401.09417 • Published Jan 17 • 58

upvoted 3 collections 10 months ago

upvoted a paper 10 months ago

MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation

Paper • 2401.04468 • Published Jan 9 • 47

upvoted a collection 10 months ago

Model Merging

Collection

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12 • 217

upvoted a paper 10 months ago

Understanding LLMs: A Comprehensive Overview from Training to Inference

Paper • 2401.02038 • Published Jan 4 • 61

upvoted a paper 11 months ago

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Paper • 2312.03694 • Published Dec 6, 2023 • 2

upvoted a paper 12 months ago

Exponentially Faster Language Modelling

Paper • 2311.10770 • Published Nov 15, 2023 • 118

Akash Singh

AI & ML interests

Organizations

akashicmarga's activity

MobileLLM

Moshi v0.1 Release

Octopus v2: On-device language model for super agent

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

StarCoder: may the source be with you!

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

ML for Tools

MoEs papers reading list

Daily Papers

MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation

Model Merging

Understanding LLMs: A Comprehensive Overview from Training to Inference

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Exponentially Faster Language Modelling