mishig (Mishig Davaadorj)

upvoted a paper 1 day ago

KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published 3 days ago • 57

upvoted an article 10 days ago

Article

LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)

By

•

9 days ago

• 31

upvoted a paper 10 days ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published 11 days ago • 226

upvoted an article 14 days ago

Article

Fine-tune Llama 3 with ORPO

By

•

11 days ago

• 151

upvoted a collection 14 days ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated 15 days ago • 454

upvoted a paper 15 days ago

The Illusion of State in State-Space Models

Paper • 2404.08819 • Published 21 days ago • 1

upvoted a paper 16 days ago

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry

Paper • 2402.04347 • Published Feb 6 • 12

upvoted 2 papers 17 days ago

LoRA: Low-Rank Adaptation of Large Language Models

Paper • 2106.09685 • Published Jun 17, 2021 • 24

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published 21 days ago • 58

upvoted a paper 19 days ago

Tutorial on Diffusion Models for Imaging and Vision

Paper • 2403.18103 • Published Mar 26 • 1

upvoted 3 papers 21 days ago

From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples

Paper • 2404.07544 • Published 22 days ago • 15

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Paper • 2404.07839 • Published 22 days ago • 36

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Paper • 2404.07143 • Published 23 days ago • 90

upvoted 2 articles 22 days ago

Article

History of State Space Models (SSM) in 2022

By

•

22 days ago

• 6

Article

It's raining diffusion personalization techniques☔️🎭🖼️

By

•

22 days ago

• 15

upvoted a paper 24 days ago

Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs

Paper • 2404.05719 • Published 25 days ago • 55

upvoted a paper 25 days ago

Formal Aspects of Language Modeling

Paper • 2311.04329 • Published Nov 7, 2023 • 1

upvoted 2 articles 27 days ago

Article

RFDiffusion Potentials

By

•

19 days ago

• 8

Article

Deploying 🤗 Hub models in Vertex AI

By

•

Feb 27

• 3

upvoted 2 articles 28 days ago

Article

Pollen-Vision: Unified interface for Zero-Shot vision models in robotics

Mar 25

• 6

Article

Diffusion Models

By

•

17 days ago

• 11

upvoted a paper 29 days ago

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published about 1 month ago • 98

upvoted 2 papers about 2 months ago

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6 • 172

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models

Paper • 2403.00818 • Published Feb 26 • 12

upvoted a paper 2 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 561

upvoted a collection 3 months ago

Qwen1.5

Collection

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated 4 days ago • 158

upvoted 4 papers 3 months ago

CroissantLLM: A Truly Bilingual French-English Language Model

Paper • 2402.00786 • Published Feb 1 • 22

MambaByte: Token-free Selective State Space Model

Paper • 2401.13660 • Published Jan 24 • 47

Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access

Paper • 2401.09967 • Published Jan 18 • 1

WARM: On the Benefits of Weight Averaged Reward Models

Paper • 2401.12187 • Published Jan 22 • 17

upvoted a collection 3 months ago

AIM

Collection

AIM: Autoregressive Image Models • 5 items • Updated Jan 29 • 43

upvoted 2 collections 4 months ago

Zeroshot Classifiers

Collection

These are my current best zeroshot classifiers. Some of my older models are downloaded more often, but the models in this collection are newer/better. • 11 items • Updated 30 days ago • 75

Mongolian Speech Models 🇲🇳

Collection

STT and TTS • 6 items • Updated Sep 8, 2023 • 2

upvoted 3 papers 4 months ago

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 152

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

Paper • 2401.02117 • Published Jan 4 • 25

Possible Meissner effect near room temperature in copper-substituted lead apatite

Paper • 2401.00999 • Published Jan 2 • 5

upvoted 2 papers 5 months ago

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention

Paper • 2312.07987 • Published Dec 13, 2023 • 39

Gated Linear Attention Transformers with Hardware-Efficient Training

Paper • 2312.06635 • Published Dec 11, 2023 • 3

upvoted a collection 5 months ago

MoE

Collection

129 items • Updated 8 days ago • 16

upvoted 3 papers 5 months ago

upvoted a collection 5 months ago

Tulu V2 Suite

Collection

The set of models associated with the paper "Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2" • 19 items • Updated Feb 1 • 43

upvoted 4 papers 5 months ago

Scalable AI Safety via Doubly-Efficient Debate

Paper • 2311.14125 • Published Nov 23, 2023 • 1

Simplifying Transformer Blocks

Paper • 2311.01906 • Published Nov 3, 2023 • 1

System 2 Attention (is something you might need too)

Paper • 2311.11829 • Published Nov 20, 2023 • 38

Transformers learn in-context by gradient descent

Paper • 2212.07677 • Published Dec 15, 2022 • 1

upvoted 2 collections 6 months ago

Zephyr 7B

Collection

Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 9 items • Updated 21 days ago • 136

Reward models on the hub

Collection

UNMAINTAINED: See RewardBench... A place to collect reward models, an often not released artifact of RLHF. • 18 items • Updated 20 days ago • 23

upvoted 2 papers 6 months ago

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Paper • 2310.04378 • Published Oct 6, 2023 • 19

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 116

upvoted a collection 7 months ago

Contra (Bottleneck T5)

Collection

Text autoencoders capable of embedding and generating text in a fixed-size latent space, useful for embeddings and latent space text editing. • 4 items • Updated Oct 3, 2023 • 27

upvoted a paper 7 months ago

Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion

Paper • 2310.03502 • Published Oct 5, 2023 • 74

upvoted a collection 7 months ago

Recent models: last 100 repos, sorted by creation date

Collection

The last 100 repos I have created. Sorted by creation date descending, so the most recently created repos appear at the top. • 121 items • Updated Jan 31 • 440

upvoted a paper 8 months ago

Code Llama: Open Foundation Models for Code

Paper • 2308.12950 • Published Aug 24, 2023 • 18

upvoted 5 papers 9 months ago

Neural signature kernels as infinite-width-depth-limits of controlled ResNets

Paper • 2303.17671 • Published Mar 30, 2023 • 1

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Paper • 2110.07205 • Published Oct 14, 2021 • 4

GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Paper • 2305.13245 • Published May 22, 2023 • 5

The First Room-Temperature Ambient-Pressure Superconductor

Paper • 2307.12008 • Published Jul 22, 2023 • 3

Completely Discretized, Finite Quantum Mechanics

Paper • 2307.11927 • Published Jul 21, 2023 • 1

Mishig Davaadorj

AI & ML interests

Articles

CodeGemma - an official Google release for code LLMs

Organizations

mishig's activity

LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)

Fine-tune Llama 3 with ORPO

History of State Space Models (SSM) in 2022

It's raining diffusion personalization techniques☔️🎭🖼️

RFDiffusion Potentials

Deploying 🤗 Hub models in Vertex AI

Pollen-Vision: Unified interface for Zero-Shot vision models in robotics

Diffusion Models