NetSpirit

netspirit

AI & ML interests

Expert integrator of local Open Source LLM & RAG solutions with sovereign and highly secure hosting. Training, knowledge transfer, case studies.

Recent Activity

upvoted a paper 1 day ago

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

liked a Space 3 months ago

Qwen/Qwen3-Omni-Demo

upvoted a collection 3 months ago

Granite 3.1 Language Models

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published 4 days ago • 198

liked a Space 3 months ago

Qwen3 Omni Demo

⚡

239

Generate audio responses from text and media inputs

upvoted a collection 3 months ago

Granite 3.1 Language Models

Collection

A series of language models with 128K context length trained by IBM licensed under Apache 2.0 license. • 9 items • Updated Nov 17, 2025 • 68

liked 2 models 3 months ago

jpacifico/Aramis-2B-BitNet-bf16

Text Generation • 2B • Updated Sep 5, 2025 • 1 • 2

Qwen/Qwen3-Embedding-8B-GGUF

8B • Updated Jul 15, 2025 • 7.42k • 98

upvoted a paper 6 months ago

AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning

Paper • 2507.12841 • Published Jul 17, 2025 • 41

upvoted a paper 9 months ago

MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft

Paper • 2504.08388 • Published Apr 11, 2025 • 42

reacted to burtenshaw's post with 🤗🚀 12 months ago

Post

3397

Manic few days in open source AI, with game changing development all over the place. Here's a round up of the resources:

- The science team at @huggingface reproduced and open source the seek r1. https://github.com/huggingface/open-r1
- @qwen released a series of models with 1 million token context! https://qwenlm.github.io/blog/qwen2.5-1m/
- SmolVLM got even smaller with completely new variants at 256m and 500m https://huggingface.co/blog/smolervlm

There's so much you could do with these developments. Especially combining them together into agentic applications or fine-tuning them on your use case.