StentorLabs/Stentor3-50M
Text Generation • 49.4M • Updated • 341 • 7
Oleg Lavrovsky PRO
loleg
AI & ML interests
Supporting Apertus team / Organizing hackathons / Engaged for open data
Recent Activity
liked a model about 21 hours ago
StentorLabs/Stentor3-50M upvoted a collection about 21 hours ago
Stentor1 liked a model about 21 hours ago
StentorLabs/Stentor-12M-InstructOrganizations
liked a
model about 21 hours ago
upvoted a collection about 21 hours ago
liked a
model about 21 hours ago
upvoted an article 2 days ago
Article
Your Agent Aced the Task. Will It Do It Again?
ibm-research
• • 112 liked a
model 2 days ago
Experimental Apertus v1.5 support for llama.cpp
❤️👍 3
6
#6 opened about 2 months ago
by 
MrMeOrYou
liked a
model 2 days ago
liked 3
models 3 days ago
reacted to Banaxi-Tech's post with 👍 4 days ago
Post
2738
We've released @BananaMindBot .
Most things you do on HuggingFace, BananaMindBot can do. Fast
Mention @BananaMindBot on a model, dataset, Space discussion, paper, blog comment, or top-level post and it'll reply there.
It's powered by North Code Mini (Qwen3.8 27B, with GPT OSS 120B as fallback).
A few things it can do:
Search for models and datasets
Look up users and orgs and see what they've published
Read model cards, configs, dataset files, blog posts, and org profiles
Answer questions about what it finds
Write and run its own code in a locked-down sandbox when it needs to verify something
Check things like a model's real parameter count from the safetensors headers instead of just repeating the model card
Remember something for later if you explicitly ask it to
Forward a message to @Banaxi-Tech
Post a daily roundup of developments in the small-language-model space
It won't execute code you give it. It can read and review that code, but anything it runs is code it wrote itself.
It also can't access private data or credentials.
Mention it somewhere.
It's going to also find this post!
(Some parts inspired by CompactBot and @CompactAI Follow them please)
Most things you do on HuggingFace, BananaMindBot can do. Fast
Mention @BananaMindBot on a model, dataset, Space discussion, paper, blog comment, or top-level post and it'll reply there.
It's powered by North Code Mini (Qwen3.8 27B, with GPT OSS 120B as fallback).
A few things it can do:
Search for models and datasets
Look up users and orgs and see what they've published
Read model cards, configs, dataset files, blog posts, and org profiles
Answer questions about what it finds
Write and run its own code in a locked-down sandbox when it needs to verify something
Check things like a model's real parameter count from the safetensors headers instead of just repeating the model card
Remember something for later if you explicitly ask it to
Forward a message to @Banaxi-Tech
Post a daily roundup of developments in the small-language-model space
It won't execute code you give it. It can read and review that code, but anything it runs is code it wrote itself.
It also can't access private data or credentials.
Mention it somewhere.
It's going to also find this post!
(Some parts inspired by CompactBot and @CompactAI Follow them please)
- 37 replies
upvoted a paper 6 days ago
liked a
model 7 days ago
liked a
dataset 8 days ago
liked a
model 8 days ago
Add LEXam-hard evaluation result
👍 1
1
#7 opened 16 days ago
by 
joelniklaus
Future architecture question
1
#6 opened 25 days ago
by 
Akicou
liked a
dataset 8 days ago
reacted to ginigen-ai's post with 🤗 8 days ago
Post
2950
OpenRouter Leaderboard — every model, every provider, one comparable table. Price, precision, uptime, measured latency and language quality on the same axes.
Building it turned up three things.
We graded 330 models on Korean and two axes collapsed.
Honorifics — only 8.5% earn an A
Knowledge of Korean institutions — 9.4%
Every other axis sits above 31%
Fluency hides it. A model can write clean, natural Korean and still attach an honorific to a coffee cup. Fluent and wrong at the same time is worse than obviously broken, because nobody catches it in review.
A 2023 model beats the 2026 flagships. gpt-3.5-turbo-16k scores a perfect 3.00. Korean cannot be inferred from release date, parameter count or English benchmarks — it has to be measured, per model.
Quality, value and speed are three different models. Across five axes, the same model almost never takes two columns.
425 models, latency measured on 329 on a paid API, Korean graded on 330. Three languages, three currencies, daily refresh, open API, no key.
📝 https://huggingface.co/blog/ginigen-ai/openrouter-leaderboard 🔎 ginigen-ai/open-router-leaderboard
Building it turned up three things.
We graded 330 models on Korean and two axes collapsed.
Honorifics — only 8.5% earn an A
Knowledge of Korean institutions — 9.4%
Every other axis sits above 31%
Fluency hides it. A model can write clean, natural Korean and still attach an honorific to a coffee cup. Fluent and wrong at the same time is worse than obviously broken, because nobody catches it in review.
A 2023 model beats the 2026 flagships. gpt-3.5-turbo-16k scores a perfect 3.00. Korean cannot be inferred from release date, parameter count or English benchmarks — it has to be measured, per model.
Quality, value and speed are three different models. Across five axes, the same model almost never takes two columns.
425 models, latency measured on 329 on a paid API, Korean graded on 330. Three languages, three currencies, daily refresh, open API, no key.
📝 https://huggingface.co/blog/ginigen-ai/openrouter-leaderboard 🔎 ginigen-ai/open-router-leaderboard
liked a
model 10 days ago
