Post
567
We need to make software where people can start using decision models.
✨ Supra2.5 coming soon
LH-Tech AI
LH-Tech-AI
AI & ML interests
Small AI and ML models at SupraLabs. Open source research. For you and the community.
Recent Activity
reacted to mithulaartigala's post with 🔥 about 8 hours ago
We need to make software where people can start using decision models.
liked a dataset about 9 hours ago
scenario-labs/3d-collection liked a model about 10 hours ago
MiniMaxAI/MiniMax-M3.1-FlashOrganizations
reacted to mithulaartigala's post with 🔥 about 8 hours ago
reacted to Banaxi-Tech's post with 😔 about 11 hours ago
Post
819
BananaMind is in the google situation before argon right now, right?
- 6 replies
reacted to DedeProGames's post with 🧠👍🤝👀➕ 3 days ago
reacted to mithulaartigala's post with 🔥 4 days ago
Post
171
Would be nice to have a 50K row decisions dataset, no? Just solve this code:
--- -.-. - --- -... . .-. --..-- / ..--- ..... - .... --..-- / ..--- ----- ..--- -.... .-.-.-
--- -.-. - --- -... . .-. --..-- / ..--- ..... - .... --..-- / ..--- ----- ..--- -.... .-.-.-
- 6 replies
replied to mithulaartigala's post 4 days ago
OCTOBER, 25TH, 2026.
replied to their post 7 days ago
Hey, yeah! Wanna cooperate with SupraLabs for that compute grant?
Message me on discord please:
lh_tech_ai
replied to their post 8 days ago
ok but i don't have time for a call/meeting now. can you DM me on discord pls?
replied to their post 8 days ago
I don't see anyone booking my calendar! Happy to talk and see if your the right fit for our program 👌
Please... can we chat on discord? lh_tech_ai is my name there
replied to their post 8 days ago
That would be cool! We are very new and the platform is not up yet so we were hoping to get some feedback during the build process ... Of course free credits as well 😃
Would you be free for a quick call so we can align?
I don't have time for a call. Can we chat on discord?
replied to their post 8 days ago
It sounds very good! Very kind of you - thanks 🤗
Maybe you can give us some credits for free so we can try out your service by renting some GPUs?
Would be really cool!
replied to their post 8 days ago
Can you message me on discord? What's your discord?
reacted to DedeProGames's post with 🔥 8 days ago
Post
8,861
🚀 Introducing Kiyo-230M-Instruct — my compact English & Portuguese chat model!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
🧠 229.7M parameters
🌍 English + Portuguese
💬 Native chat template for multi-turn conversations
📏 2,048-token context window
📦 459 MB of BF16 safetensors weights
🔓 Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. I’m excited to share it with people exploring how much we can get from small, accessible models!
🤗 Model & full README:
DedeProGames/Kiyo-230M-Instruct
💬 Try the chat demo:
DedeProGames/kiyo-230m-chat
Try it in English or Portuguese — I’d love to see your examples, feedback, and experiments!
Built on Kiyo-230M-Preview, a base model I pretrained from scratch, Kiyo now has an instruction-tuned release for everyday conversations, rewriting, and lightweight assistant experiments.
🧠 229.7M parameters
🌍 English + Portuguese
💬 Native chat template for multi-turn conversations
📏 2,048-token context window
📦 459 MB of BF16 safetensors weights
🔓 Apache-2.0 license
For instruction tuning, I used 165,735 conversations from SmolTalk2, smol-smoltalk, UltraChat, and Dolci-Instruct-SFT. Training ran for two complete epochs with assistant-only loss, using a roughly 70% English / 30% Portuguese token mix.
The updated model card includes benchmarks against SmolLM2-135M-Instruct, BananaMind, and Supra2, plus example conversations, CPU measurements, training details, and a Transformers quickstart.
The results are mixed: Kiyo is competitive with these small models across the reported evaluations, while SmolLM2 and BananaMind score higher on the instruction-following benchmarks. Portuguese was a highlight in the small conversational sanity test.
This is an experimental 230M model, with plenty of room to improve reasoning, factual accuracy, and strict instruction following. I’m excited to share it with people exploring how much we can get from small, accessible models!
🤗 Model & full README:
DedeProGames/Kiyo-230M-Instruct
💬 Try the chat demo:
DedeProGames/kiyo-230m-chat
Try it in English or Portuguese — I’d love to see your examples, feedback, and experiments!
- 9 replies
reacted to wayneworkman2012's post with 🔥👍➕🚀 9 days ago
Post
3,178
To all the inference providers behind the HuggingFace router - if you want me to use your services you will have to serve native-precision models. I'm not paying for FP8 when I can run in bf16 locally.
- 6 replies