Júlio César

Ramikan-BR

AI & ML interests

Enthusiast AI, SLM, AI Coder... in search of small, powerful, lightweight AI models that run without a GPU on weak computers.

Organizations

Ramikan-BR's activity

upvoted a collection 10 days ago

4M Models

Collection

Multimodal models from https://4m.epfl.ch/ • 14 items • Updated 18 days ago • 29

upvoted a collection 14 days ago

4bit Instruct Models

Collection

10 items • Updated 24 days ago • 11

upvoted a collection 15 days ago

Depth Anything v2 Release

Collection

A comprehensive collection on DAv2 • 5 items • Updated 15 days ago • 8

upvoted an article 29 days ago

Article

Uncensor any LLM with abliteration

•

20 days ago

• 226

upvoted 2 collections about 1 month ago

ZeroGPU Spaces

Collection

ZeroGPU Spaces made by the community • 17 items • Updated 27 days ago • 206

everything-ai

Collection

upvoted an article about 1 month ago

Article

GPU Poor Savior: Revolutionizing Low-Bit Open Source LLMs and Cost-Effective Edge Computing

•

May 25

• 9

upvoted a paper about 1 month ago

Retrieving Texts based on Abstract Descriptions

Paper • 2305.12517 • Published May 21, 2023 • 2

upvoted a collection about 1 month ago

LLM Leaderboard best models ❤️‍🔥

Collection

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 264 items • Updated 10 days ago • 342

upvoted a collection about 2 months ago

My Best Spaces

Collection

My most polished spaces • 7 items • Updated May 12 • 35

upvoted an article about 2 months ago

Article

🦙⚗️ Using Llama3 and distilabel to build fine-tuning datasets

•

29 days ago

• 64

upvoted a paper about 2 months ago

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12 • 62

upvoted a collection about 2 months ago

fuck quadratic attention

Collection

11 items • Updated Apr 24 • 20

upvoted an article 2 months ago

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 26

upvoted a collection 2 months ago

Load 4bit models 4x faster

Collection

Native bitsandbytes 4bit pre quantized models • 17 items • Updated 24 days ago • 32

upvoted an article 2 months ago

Article

How to Finetune phi-3 on MacBook Pro

•

Apr 24

• 59

upvoted a paper 2 months ago

Sabiá: Portuguese Large Language Models

Paper • 2304.07880 • Published Apr 16, 2023 • 4

upvoted 3 collections 3 months ago

upvoted a collection 4 months ago

Recent models: last 100 repos, sorted by creation date

Collection

The last 100 repos I have created. Sorted by creation date descending, so the most recently created repos appear at the top. • 121 items • Updated Jan 31 • 463