Cosmo's picture

Cosmo

cosmojg

·

https://cosmo.red

cosmojg

cosmojg

AI & ML interests

Machine learning and computational neuroscience

Organizations

None yet

cosmojg's activity

upvoted a collection 17 days ago

Core ML Gallery Models

7 items • Updated 12 days ago • 25

upvoted an article 18 days ago

Article

Uncensor any LLM with abliteration

By

•

18 days ago

• 223

upvoted a collection 19 days ago

GLM-4

GLM-4 Open Models • 4 items • Updated 26 days ago • 80

upvoted an article 28 days ago

Article

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

By

•

Apr 24

• 51

upvoted a collection about 1 month ago

C4AI Aya 23

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 3 items • Updated May 23 • 38

upvoted an article about 1 month ago

Article

License to Call: Introducing Transformers Agents 2.0

May 13

• 98

upvoted a collection about 2 months ago

Yi-1.5 (2024/05)

10 items • Updated May 20 • 82

upvoted an article about 2 months ago

Article

Expanding Model Context and Creating Chat Models with a Single Click

By

•

Apr 28

• 35

upvoted an article 2 months ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 144

upvoted a paper 2 months ago

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

Paper • 2309.10400 • Published Sep 19, 2023 • 23

upvoted 3 collections 2 months ago

📀 Dataset comparison models

1.8B models trained on 350BT to compare different pretraining datasets • 8 items • Updated 19 days ago • 25

OpenELM Instruct Models

4 items • Updated 12 days ago • 106

OpenELM Pretrained Models

4 items • Updated 12 days ago • 43

upvoted 4 papers 2 months ago

Transformers Can Represent n-gram Language Models

Paper • 2404.14994 • Published Apr 23 • 18

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12 • 59

AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation

Paper • 2404.12753 • Published Apr 19 • 39

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Paper • 2307.01952 • Published Jul 4, 2023 • 75

upvoted a collection 2 months ago

WizardLM

0 items • Updated May 8 • 100

upvoted a paper 3 months ago

Compression Represents Intelligence Linearly

Paper • 2404.09937 • Published Apr 15 • 27

upvoted an article 3 months ago

Article

CodeGemma - an official Google release for code LLMs

Apr 9

• 98

upvoted a collection 3 months ago

MGM

Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 13 items • Updated May 3 • 45

upvoted a paper 4 months ago

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

Paper • 2402.17764 • Published Feb 27 • 574

upvoted 2 collections 4 months ago

MiquMaid

6 items • Updated Apr 30 • 11

My favorite models (benchs+usage/feel+innovation)

How I select models ? First, I bench them, to trim the overfit & dumbified models. Then, I test them. The smartest to my taste end-up here. • 10 items • Updated May 11 • 7

upvoted 2 collections 8 months ago

Nemotron 3 8B

The Nemotron 3 8B Family of models is optimized for building production-ready generative AI applications for the enterprise. • 5 items • Updated 17 days ago • 41

Favorites

10 items • Updated Mar 18 • 1

upvoted a paper 8 months ago

Textbooks Are All You Need II: phi-1.5 technical report

Paper • 2309.05463 • Published Sep 11, 2023 • 84

upvoted a collection 8 months ago

Zephyr 7B

Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 9 items • Updated Apr 12 • 141