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 about 8 hours ago

guidelabs/steerling-8b

upvoted a collection 5 days ago

jina-embeddings-v5-text

liked a model 6 days ago

View all activity

Organizations

upvoted a collection 5 days ago

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 23 items • Updated 6 days ago • 30

upvoted a paper 7 days ago

PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models

Paper • 2602.06053 • Published Jan 14 • 6

upvoted an article 11 days ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

12 days ago

•

45

upvoted a collection 20 days ago

Qwen3-Coder-Next

4 items • Updated 21 days ago • 95

upvoted an article 27 days ago

Article

Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek

28 days ago

•

45

upvoted a collection about 1 month ago

Qwen3-TTS

7 items • Updated Jan 22 • 306

upvoted an article about 1 month ago

Article

Open Responses: What you need to know

+2

Jan 15

•

108

upvoted a paper about 1 month ago

Ministral 3

Paper • 2601.08584 • Published Jan 13 • 54

upvoted an article about 2 months ago

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

+4

Dec 18, 2025

•

120

upvoted 2 collections about 2 months ago

T5Gemma 2

3 items • Updated Dec 18, 2025 • 66

💧 LFM2.5

Collection of Instruct, Base, and Japanese LFM2.5-1.2B models. • 22 items • Updated about 1 hour ago • 93

upvoted 3 collections 3 months ago

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 155

Quantized Olmo 3

Verified models. All compatible with vLLM for very fast inference. Use the 3.1 models as they are more recent. • 23 items • Updated Dec 15, 2025 • 4

jina-code-embeddings

high quality code embeddings trained from code generation models • 5 items • Updated Sep 3, 2025 • 13

upvoted an article 3 months ago

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

330

upvoted a collection 3 months ago

Depth Anything 3

12 items • Updated Dec 11, 2025 • 25

upvoted a paper 3 months ago

Depth Anything 3: Recovering the Visual Space from Any Views

Paper • 2511.10647 • Published Nov 13, 2025 • 99

upvoted 2 collections 3 months ago

Olmo 3

Artifacts for the Olmo 3 release. • 9 items • Updated Dec 23, 2025 • 164

SAM3

4 items • Updated Nov 19, 2025 • 23

upvoted an article 4 months ago

Article

Re-understanding KL Approximation from an RL-for-LLM Lens: Notes on “Approximating KL Divergence”

Aug 11, 2025

•

8