pascalmusabyimana's picture

pascalmusabyimana

pascal-maker

·

https://pascal-maker.github.io/developedbypascalmusabyimana/

AI & ML interests

computer vision, nlp , machine learning and deeplearning

Recent Activity

liked a model 1 day ago

Qwen/Qwen-Image

reacted to salma-remyx's post with 👀 1 day ago

𝗣𝗮𝗽𝗲𝗿𝟮𝗣𝗥𝘀 Lately, we've been experimenting with recommending arXiv papers based on the context of what we're building in AI. At the same time, we're using an agent to help automate the building and testing of Docker Images. Check out the example here: https://hub.docker.com/repository/docker/remyxai/2507.20613v1/general Next, we're tasking our #ExperimentOps agent to open PRs in a target repo, to evaluate the core concepts from a new research paper in the context of your application and your kpis. Operationalize your Experimentation! Find Your Frontier! #BeAnExperimenter

liked a model 5 days ago

openai/gpt-oss-20b

View all activity

Organizations

upvoted a collection 13 days ago

GLM-4.5

10 items • Updated 7 days ago • 197

upvoted a collection 20 days ago

OpenReasoning-Nemotron

Collection of models for OpenReasoning-Nemotron which are trained on 5M reasoning traces for Math, Code and Science. • 6 items • Updated 11 days ago • 39

upvoted a collection 23 days ago

🚀 Optimized Models: torchao & Pruna Quantization

Quantized Models using torchao & Pruna for efficient inference and deployment. • 8 items • Updated 4 days ago • 1

upvoted a collection 27 days ago

Releases July 4

25 items • Updated Jul 7 • 7

upvoted a paper about 1 month ago

MedGemma Technical Report

Paper • 2507.05201 • Published Jul 7 • 14

upvoted 2 articles about 1 month ago

Article

Creating custom kernels for the AMD MI300

By

and 1 other •

Jul 9

• 43

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

Jul 8

• 615

upvoted 2 collections about 1 month ago

🍉 June 2025 - Open works from the Chinese community

29 items • Updated 14 days ago • 7

ERNIE 4.5

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 25 items • Updated about 1 month ago • 157

upvoted a paper about 1 month ago

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Paper • 2506.11763 • Published Jun 13 • 69

upvoted 2 articles about 2 months ago

Article

Gemma 3n fully available in the open-source ecosystem!

By

and 7 others •

Jun 26

• 114

Article

Transformers backend integration in SGLang

By

and 4 others •

Jun 23

• 50

upvoted a collection about 2 months ago

Releases June 13

40 items • Updated Jun 18 • 5

upvoted an article about 2 months ago

Article

MCP is at a Tipping Point: Here's Why You Should Care

By

•

Jun 10

• 17

upvoted a collection about 2 months ago

Qwen3

84 items • Updated 5 days ago • 1.05k

upvoted 2 articles about 2 months ago

Article

Sensitivity Aware Mixed Precision Quantization V1

By

and 1 other •

Jun 13

• 19

Article

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

By

and 5 others •

Jun 3

• 81

upvoted a collection 2 months ago

V-JEPA 2

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13 • 154

upvoted a collection 3 months ago

Any-to-Any Models, Datasets, Spaces

18 items • Updated Jun 20 • 23

upvoted an article 3 months ago

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

By

and 3 others •

May 23

• 154