Victor Jotham Ashioya's picture

Victor Jotham Ashioya

ashioyajotham

·

https://ashioyajotham.github.io/

AI & ML interests

Hallucination in LLMs, AI Safety: alignment, red-teaming

Recent Activity

liked a Space 7 days ago

HuggingFaceFW/blogpost-fineweb-v1

updated a Space 17 days ago

ashioyajotham/falcon_7b_coder

updated a collection 19 days ago

View all activity

Organizations

None yet

ashioyajotham's activity

liked a Space 7 days ago

FineWeb: decanting the web for the finest text data at scale

Generate high-quality web text data for LLM training

updated a Space 17 days ago

Falcon 7b Coder

updated a collection 19 days ago

LLM Reasoning

6 items • Updated 19 days ago

upvoted a paper 19 days ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 19 days ago • 105

updated a collection 19 days ago

LLM Reasoning

6 items • Updated 19 days ago

upvoted a paper 19 days ago

Towards General-Purpose Model-Free Reinforcement Learning

Paper • 2501.16142 • Published 20 days ago • 26

liked 3 models about 1 month ago

meta-llama/Meta-Llama-3-8B

Text Generation • Updated Sep 27, 2024 • 607k • 6.03k

meta-llama/Llama-3.1-70B-Instruct

Text Generation • Updated Dec 15, 2024 • 376k • • 787

meta-llama/Llama-2-7b-hf

Text Generation • Updated Apr 17, 2024 • 1.26M • 1.94k

liked a dataset about 1 month ago

databricks/databricks-dolly-15k

Viewer • Updated Jun 30, 2023 • 15k • 15.4k • 792

liked a Space 4 months ago

Qwen2.5 Math Demo

Describe math images and answer questions

liked a dataset 5 months ago

openai/MMMLU

Viewer • Updated Oct 16, 2024 • 393k • 15k • 453

updated a collection 6 months ago

Fav papers

28 items • Updated Aug 24, 2024

upvoted a paper 6 months ago

Sapiens: Foundation for Human Vision Models

Paper • 2408.12569 • Published Aug 22, 2024 • 90

updated a collection 9 months ago

Fav papers

28 items • Updated Aug 24, 2024

upvoted a paper 9 months ago

Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach

Paper • 2405.15613 • Published May 24, 2024 • 15

updated a collection 9 months ago

VLMs

1 item • Updated May 28, 2024

upvoted a paper 9 months ago

An Introduction to Vision-Language Modeling

Paper • 2405.17247 • Published May 27, 2024 • 87

liked a model 9 months ago

internlm/internlm2-math-plus-mixtral8x22b

Text Generation • Updated May 24, 2024 • 16 • 17