Hugging Face's logo
Dokyoon's picture

Dokyoon

leeloolee
120 338
maywell's profile picture kaki-paper's profile picture shootstufff's profile picture
Ā·

AI & ML interests

ai

Recent Activity

reacted to DedeProGames's post with šŸ”„ 1 day ago
šŸš€ Introducing OpenWork ā€” Deploy agents everywhere. OpenWork is an open-source AI agent workspace built on top of OpenCode. Deploy autonomous agents, schedule tasks, manage projects, and let AI work for you ā€” directly from your terminal. Features: - šŸ¤– Deploy autonomous AI agents - šŸ“… Schedule recurring tasks - šŸ§  Persistent memory and workspaces - šŸ”Œ MCP integrations and custom tools - šŸ“„ Agent Inbox and task management -āš” Support for local and cloud AI models - šŸ–„ļø Interactive terminal interface (TUI) Your agents. Your models. Your workflow. Fully open-source. MIT licensed. ā­ GitHub: https://github.com/dedeprogames-official/openwork #OpenSource #AI #AIAgents #OpenWork #OpenCode
reacted to SeaWolf-AI's post with šŸ”„ 2 days ago
šŸ† Darwin-27B-ZTC-v2 just took #1 on the System One Mosaic Benchmark (S1MB). S1MB compares 102 models across 137 specialized benchmarks, in three task types: Noul (assess a condition), Choice (select an option), Score (rate on a scale). Ranking is by overall Borda score. šŸ“Š Top of the board šŸ„‡ Darwin ZTC v2 (FINAL-Bench) 89.58 šŸ„ˆ OpenJev-27B 87.50 šŸ„‰ AutoJev-27B 87.07 4ļøāƒ£ Eikos 27B 85.43 5ļøāƒ£ Jev 1.13 85.05 šŸ”Ž Ranks 2 to 5 are all the JEV family (TypeSafe AI's System One model, from ex-OpenAI researchers). S1MB exists to compare these System One judges, so leading it is the headline. āš™ļø Why a zero-token judge wins here šŸ”¹ It does not generate. It reads the input and typed questions and returns a calibrated distribution in a single forward pass. šŸ”¹ Zero generated tokens, no decoding loop, so latency and cost stay low. šŸ”¹ Holds up out of distribution too: General Noul 96.00, General Choice 99.34. It is also #1 on the typed-decisions leaderboard (0.743, zero-shot). Same message from both: a deterministic, calibrated judge at one forward pass per call. šŸ”— Model: https://huggingface.co/FINAL-Bench/Darwin-27B-ZTC-v2 šŸ”— Leaderboard: https://huggingface.co/spaces/hotchpotch/S1MB-leaderboard Standings move as new models are added. Numbers reflect the board at the time of writing. šŸ™Œ
upvoted a collection 14 days ago
NLA Models
View all activity

Organizations

HAE-RAE's profile picture MultišŸ¤–Transformers's profile picture ģøģŠ¤ķŠøėŸ­ķŠø.ķ•œźµ­'s profile picture Pi3AI's profile picture nanochat students's profile picture ETRI Economic Forecasting AI Lab's profile picture ML intern explorers's profile picture