D. Danchev's picture

D. Danchev

danchev

·

https://www.ai-engineer.com

AI & ML interests

Open Source AI

Recent Activity

updated a model 1 day ago

danchev/ibm-granite-docling-258M-GGUF

liked a Space 2 days ago

ibm-granite/granite-docling-258M-WebGPU

upvoted a collection 6 days ago

Granite 4.0 Language Models

View all activity

Organizations

upvoted a collection 6 days ago

Granite 4.0 Language Models

11 items • Updated about 5 hours ago • 133

upvoted an article 7 days ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

By

and 5 others •

Sep 4

• 232

upvoted 2 collections 20 days ago

Gemma Family

LiteRT models in the Gemma Family • 11 items • Updated 28 days ago • 12

Web Models

LiteRT models that can run on the Web • 8 items • Updated 28 days ago • 4

upvoted an article 27 days ago

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

By

and 6 others •

28 days ago

• 152

upvoted 2 collections about 2 months ago

NVIDIA Nemotron

Open, Production-ready Enterprise Models. Nvidia Open Model license. • 4 items • Updated 1 day ago • 62

GPT OSS

2 items • Updated Aug 20 • 11

upvoted 2 collections 3 months ago

T5Gemma

32 items • Updated Jul 10 • 73

Gemma 3n

4 items • Updated Jul 10 • 231

upvoted 3 collections 5 months ago

Gemma 3n Preview

4 items • Updated Jul 10 • 179

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 209

BgGPT-Gemma-2

BgGPT-Gemma-2 collection of models. • 6 items • Updated about 16 hours ago • 14

upvoted 2 collections 6 months ago

Llama 4

Meta's new Llama 4 multimodal models, Scout & Maverick. Includes Dynamic GGUFs, 16-bit & Dynamic 4-bit uploads. Run & fine-tune them with Unsloth! • 15 items • Updated 7 days ago • 49

Llama 4

Llama 4 release • 13 items • Updated Apr 29 • 633

upvoted an article 7 months ago

Article

Introduction to ggml

By

and 2 others •

Aug 13, 2024

• 242

upvoted an article 8 months ago

Article

We now support VLMs in smolagents!

By

and 2 others •

Jan 24

• 109

upvoted 2 collections 9 months ago

Phi-4

Phi-4 family of small language, multi-modal and reasoning models. • 17 items • Updated Jul 10 • 183

DeepSeek-V3

4 items • Updated Mar 25 • 276

upvoted a collection 10 months ago

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated Apr 30 • 100

upvoted a collection 11 months ago

PixMo

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 10 items • Updated Apr 30 • 80