James PRO

jtatman

AI & ML interests

improving domain specific models and re-sampling data, refining datasets for use in different modalities, small scale micro-llm clusters using quantized and smoothed models, and all emerging llm stack connecting technologies. Small models rock.

Recent Activity

liked a dataset 2 days ago

Locutusque/hercules-v6.9

liked a model 3 days ago

deepseek-ai/Janus-Pro-1B

liked a model 19 days ago

nvidia/AceInstruct-1.5B

View all activity

Organizations

jtatman's activity

upvoted a paper 2 months ago

Hymba: A Hybrid-head Architecture for Small Language Models

Paper • 2411.13676 • Published Nov 20, 2024 • 41

upvoted a paper 5 months ago

Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance

Paper • 2409.04593 • Published Sep 6, 2024 • 25

upvoted a collection 7 months ago

Llama 3.1

Collection

This collection hosts the transformers and original repos of the Llama 3.1, Llama Guard 3 and Prompt Guard models • 11 items • Updated Dec 6, 2024 • 645

upvoted an article 7 months ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23, 2024

• 226

upvoted a paper 7 months ago

Retrieval-Enhanced Machine Learning: Synthesis and Opportunities

Paper • 2407.12982 • Published Jul 17, 2024 • 6

upvoted a paper 8 months ago

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch

Paper • 2406.14563 • Published Jun 20, 2024 • 30

upvoted an article 8 months ago

Article

Welcome Gemma - Google's new open LLM

Feb 21, 2024

• 21

upvoted a collection 8 months ago

abliterated-v3

Collection

Latest gen of the abliterated models I've produced • 17 items • Updated Jun 3, 2024 • 108

upvoted an article 9 months ago

Article

SeeMoE: Implementing a MoE Vision Language Model from Scratch

•

Jun 23, 2024

• 33

upvoted a paper 11 months ago

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Paper • 2403.03853 • Published Mar 6, 2024 • 62

upvoted 4 papers about 1 year ago

Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers

Paper • 2311.10642 • Published Nov 17, 2023 • 24