Juk Armstrong's picture

Juk Armstrong

jukofyork

·

jukofyork

AI & ML interests

None yet

Recent Activity

new activity 6 days ago

daavidhauser/chess-bot-3000-250m:The "Softmax Bottleneck" might be interesting to look at

new activity 13 days ago

jukofyork/creative-writing-control-vectors-v3.0:“The doom lies in yourself, not in your name.”

liked a model 22 days ago

TheDrummer/Precog-123B-v1

View all activity

Organizations

None yet

upvoted a paper about 2 months ago

Tensor Logic: The Language of AI

Paper • 2510.12269 • Published Oct 14 • 7

upvoted a collection 2 months ago

Foundation Text-Generation Models Below 360M Parameters

Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. • 41 items • Updated Oct 4 • 37

upvoted 2 articles 11 months ago

Article

Exploring Name Diversity in Modern LLMs: A Grimdark Trilogy Experiment

Sep 27, 2024

•

10

Article

Releasing QwQ-LongCoT-130K

Dec 5, 2024

•

10

upvoted 2 collections 12 months ago

K2-V1

K2, LLM360's most powerful, scaled model series. • 7 items • Updated 2 days ago • 11

NOSLOP

Large language models which were NOT trained on synthetic data. • 8 items • Updated Oct 16, 2024 • 1

upvoted an article about 1 year ago

Article

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

Dec 4, 2024

•

80

upvoted 2 collections over 1 year ago

Miqu-based Models

A collection of creative writing models based on the 'miqu-1-70b ' model. • 9 items • Updated Oct 26 • 2

dbrx-16x12b-instruct-gguf

GGUF quantum models for DBRX: https://github.com/ggerganov/llama.cpp • 6 items • Updated Apr 14, 2024 • 1