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.
Recent Activity
upvoted a paper 2 months ago
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code
Generation reacted to imnotkitty's post with 🚀 3 months ago
The 2025 Chinese LLM Showdown: Western Models Still Dominate Top 4, but China Leads the Open-Source Arena.
🏆 The Champions: Claude-Opus-4.5, Gemini-3-Pro, GPT-5.2, and Gemini-3-Flash sweep the top four spots.
🚀 The Pursuers: Doubao and DeepSeek-V3.2 tie for first place among Chinese models; GLM-4.7, ERNIE-5.0, and Kimi secure their positions in the domestic top five.
🔥 The Biggest Highlight: The top three spots on the open-source leaderboard are entirely held by Team China (DeepSeek, GLM, Kimi), outperforming the best western open-source models. liked a model 4 months ago
WizardLMTeam/WizardCoder-Python-34B-V1.0Organizations
-
Open LLM Leaderboard
🏆14kTrack, rank and evaluate open LLMs and chatbots
-
Open LLM Leaderboard Results PR Opener
🧐54Update model card with Open LLM Leaderboard results
-
Subquadratic LLM Leaderboard
🏆20Submit models for evaluation on a leaderboard
-
Open Portuguese LLM Leaderboard
🏆244Track, rank and evaluate open LLMs in Portuguese
I'm learning how to refine an AI model with Unsloth, but I suffer from catastrophic forgetfulness that lowers the AI average when changing the dataset
-
Open LLM Leaderboard
🏆14kTrack, rank and evaluate open LLMs and chatbots
-
Open LLM Leaderboard Results PR Opener
🧐54Update model card with Open LLM Leaderboard results
-
Subquadratic LLM Leaderboard
🏆20Submit models for evaluation on a leaderboard
-
Open Portuguese LLM Leaderboard
🏆244Track, rank and evaluate open LLMs in Portuguese
I'm learning how to refine an AI model with Unsloth, but I suffer from catastrophic forgetfulness that lowers the AI average when changing the dataset