Tech Dev

techdef215

·

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF

upvoted a collection 4 days ago

JOSIE-2 4B Preview

liked a model 14 days ago

prism-ml/Ternary-Bonsai-27B-gguf

View all activity

Organizations

None yet

upvoted a collection 4 days ago

JOSIE-2 4B Preview

The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 9 items • Updated about 10 hours ago • 4

upvoted a collection 14 days ago

Bonsai 27B

10 items • Updated 14 days ago • 202

upvoted 3 collections about 2 months ago

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated Jun 15 • 106

Mellum 2

Mellum2 model weights • 6 items • Updated Jun 1 • 126

dots.tts

dots.tts • 6 items • Updated about 8 hours ago • 15

upvoted a collection 2 months ago

MiniCPM5

A SOTA 1B on-device LLM, small yet powerful. • 11 items • Updated May 26 • 40

upvoted a collection 4 months ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 10 days ago • 250

upvoted 5 collections 5 months ago

Qwen3.5-MNN

Qwen3.5 MNN Models. • 13 items • Updated Mar 4 • 2

Jan-code

2 items • Updated Mar 2 • 21

Qwen3.5

21 items • Updated Mar 9 • 1.74k

Spanish PII & De-Identification

33 models for Spanish PII detection & de-identification. 55+ entity types. HIPAA & GDPR compliant. Apache 2.0. • 35 items • Updated 15 days ago • 4

Tiny Aya

Bridging Scale and Multilingual Depth • 10 items • Updated Feb 17 • 77

upvoted 2 collections 6 months ago

AgentDoG

A Diagnostic Guardrail Framework for AI Agent Safety and Security • 12 items • Updated Jun 21 • 112

RynnBrain

11 items • Updated Apr 13 • 25

upvoted 5 collections 9 months ago

Ouro

a family of pre-trained Looped Language Models. • 4 items • Updated Oct 29, 2025 • 35

JanusCoder

8 items • Updated Feb 2 • 12

Granite 4.0 Nano Language Models

Ultra-compact language models designed for the edge and on-device deployment. • 9 items • Updated Apr 29 • 103

Reasoning Efficiency Research

Ultra-efficient reasoning model! SOTA Accuracy / CoT Length trade-offs • 3 items • Updated 12 days ago • 14

LightOnOCR 🦉

The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR • 6 items • Updated Jun 24 • 16

upvoted a collection 10 months ago

AndesVL

AndesVL is a suite of mobile-optimized Multimodal Large Language Models (MLLMs) with 0.6B to 4B parameters. • 8 items • Updated Feb 1 • 15