Marcello Seri

mseri

·

https://mseri.me

AI & ML interests

None yet

Recent Activity

liked a model 2 days ago

LiquidAI/LFM2.5-VL-3B-DSpark

liked a model 2 days ago

ukisai/Swift-Bonsai-2-GGUF

liked a model 3 days ago

apple/LensVLM-9B

View all activity

Organizations

upvoted a paper 3 days ago

LensVLM: Selective Context Expansion for Compressed Visual Representation of Text

Paper • 2605.07019 • Published May 7 • 6

upvoted 2 collections 3 days ago

Bonsai-2

4 items • Updated 9 days ago • 152

Bonsai 27B

10 items • Updated Jul 15 • 248

upvoted a collection 12 days ago

Granite 4.2 Language Models

Efficient reasoning and thinking language models for multilingual generation, coding, and AI assistant workflows. • 24 items • Updated 12 days ago • 42

upvoted 2 collections 23 days ago

Granite Speech

Multilingual ASR and speech-to-text (STT) models for enterprise transcription and translation. • 11 items • Updated Aug 20 • 39

K2 Horizon

K2 Horizon models, datasets, and supporting resources • 22 items • Updated 16 days ago • 135

upvoted a collection about 1 month ago

Muse Glimmer

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated Aug 10 • 109

upvoted a collection 2 months ago

Luciole LLM

Open Source LLM in French, English, German, Spanish, Italian, Portuguese, Dutch and Arabic • 19 items • Updated 3 days ago • 14

upvoted a collection 3 months ago

DFlash

Block Diffusion for Flash Speculative Decoding • 23 items • Updated 14 days ago • 156

upvoted an article 3 months ago

Article

Why Specialization Is Inevitable

Dharma-AI

•

Jun 30

• 19

upvoted 2 collections 3 months ago

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 7 days ago • 394

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 20 items • Updated Aug 14 • 113

upvoted 4 collections 4 months ago

Mellum 2

Mellum2 model weights • 6 items • Updated Jun 1 • 133

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated Aug 26 • 124

Gemma 4 QAT Mobile

4 items • Updated Jul 21 • 52

Gemma 4 QAT Q4_0

19 items • Updated Jul 21 • 162

upvoted an article 5 months ago

Article

Granite 4.1 LLMs: How They’re Built

ibm-granite

•

Apr 29

• 93

upvoted 2 collections 5 months ago

DeepSeek-V4

10 items • Updated 17 days ago • 918

Ternary Bonsai

1.58-bit Bonsai models • 9 items • Updated Jun 4 • 108

upvoted a collection 6 months ago

Introspective Diffusion Language Models (I-DLM)

Model checkpoints for I-DLM. Paper: https://arxiv.org/abs/2604.11035 • 3 items • Updated Apr 14 • 11