Nick Doiron's picture

Nick Doiron

monsoon-nlp

·

AI & ML interests

biology and multilingual models

Recent Activity

liked a model 7 days ago

AI4PD/ZymCTRL

upvoted an article 13 days ago

They Said It Couldn’t Be Done

upvoted a collection 13 days ago

U-MATH and μ-MATH - University-level math evaluation

View all activity

Articles

Abliterating Refusal and Code LLMs

Starting Tiny with Protein LLaMA

Protein similarity and Matryoshka embeddings

Trying IDEFICS on a New Yorker cartoon dataset

Organizations

monsoon-nlp's activity

upvoted an article 13 days ago

Article

They Said It Couldn’t Be Done

By

•

20 days ago

• 75

upvoted a collection 13 days ago

U-MATH and μ-MATH - University-level math evaluation

Paper: A UNIVERSITY-LEVEL BENCHMARK FOR EVALUATING MATHEMATICAL SKILLS IN LLMS • 3 items • Updated 13 days ago • 15

upvoted 2 papers 16 days ago

Monet: Mixture of Monosemantic Experts for Transformers

Paper • 2412.04139 • Published 20 days ago • 10

LoFiT: Localized Fine-tuning on LLM Representations

Paper • 2406.01563 • Published Jun 3 • 1

upvoted a paper 28 days ago

Farmer.Chat: Scaling AI-Powered Agricultural Services for Smallholder Farmers

Paper • 2409.08916 • Published Sep 13 • 3

upvoted 2 collections about 1 month ago

Plant foundation models

A collection of pre-trained DNA models for plant genomes. • 19 items • Updated Oct 23 • 4

Malaysian synthetic dataset

Use LLM to generate Malaysian context synthetic dataset. • 33 items • Updated 3 days ago • 1

upvoted a paper about 1 month ago

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Paper • 2411.07781 • Published Nov 12 • 1

upvoted a paper about 2 months ago

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

Paper • 2410.20771 • Published Oct 28 • 3

upvoted a collection 2 months ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 19 days ago • 548

upvoted an article 4 months ago

Article

Building DoRA Support for Embedding Layers in PEFT

By

•

Aug 23

• 10

upvoted a paper 4 months ago

To Code, or Not To Code? Exploring Impact of Code in Pre-training

Paper • 2408.10914 • Published Aug 20 • 41

upvoted a paper 5 months ago

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17 • 2

upvoted a collection 5 months ago

PlantCaduceus (512bp len)

https://plantcaduceus.github.io • 8 items • Updated 7 days ago • 2

upvoted a paper 6 months ago

Larimar: Large Language Models with Episodic Memory Control

Paper • 2403.11901 • Published Mar 18 • 32

upvoted a collection 6 months ago

Cambrian-1 Models

6 items • Updated Jun 28 • 20

upvoted an article 6 months ago

Article

Recommendation to Revisit the Diffuser Default LoRA Parameters

By

•

Jun 21

• 11

upvoted a paper 6 months ago

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Paper • 2406.10209 • Published Jun 14 • 8

upvoted a collection 6 months ago

Florence

9 items • Updated Jul 11 • 160

upvoted a paper 7 months ago

A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding

Paper • 2406.05540 • Published Jun 8 • 3