A hat is cool a brain chip is uuuh weird
🏗️ Building on HF
Boning Cui
Bc-AI
AI & ML interests
He/Him. I like LLM's and VLM's. I work with my other friends to make stuff. We are in year 7 and we are enthusiastic about AI. We are based in Australia 🇦🇺 (QLD Btw)
Recent Activity
new activity about 7 hours ago
Banaxi-Tech/test-model:im making a agent app for orion too lol upvoted a collection about 8 hours ago
Bonsai 2 Small new activity about 10 hours ago
SupraLabs/SupraBrain-50M:Amazing workOrganizations
replied to Banaxi-Tech's post about 11 hours ago
replied to Banaxi-Tech's post about 18 hours ago
well as long as its not in my brain im happy a hat or smth yes
replied to Banaxi-Tech's post about 18 hours ago
This comment has been hidden
replied to DedeProGames's post 1 day ago
Congrats!
reacted to DedeProGames's post with 🤯🚀🧠🔥 1 day ago
Post
7,881
🚀 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!
- 3 replies
replied to LH-Tech-AI's post 1 day ago
Oh in no way did I mean any offence. Just meant I couldn’t book calls lol. Anyways thanks for you time
replied to LH-Tech-AI's post 1 day ago
@SingleSkyBradley i am a year 7 student I cannot call random people online
replied to LH-Tech-AI's post 1 day ago
bruh i have a i5-1335u laptop of course i will
replied to LH-Tech-AI's post 1 day ago
@SingleSkyBradley I am a year 7 ai developer and i would really appreciate some credits to help me develop my AI models. I will be happy to provide feedback too!
reacted to loleg's post with 🤯❤️🤗 1 day ago
Post
3,746
My colleagues – the talented scientists and engineers behind the Apertus models @swiss-ai – continue to resolve issues and respond to questions about the 1.5 release, at the same time as we continue work on the roadmap to 2.0. Today we celebrate our next milestone: the new Technical Report has months of evaluation and analysis in one heap of a preprint 📚 See our new post for a summary, and please 🤗 upvote!
https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes
https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes
- 1 reply
replied to mithulaartigala's post 2 days ago
Trust lol
reacted to Banaxi-Tech's post with 🚀🔥👀🤗 3 days ago
Post
3,743
KV1 updates:
We at klein-ml have finished stage 1 of KV1 1.2B, we don't think we will need additional stages.
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at klein-ml are working on Klein 24B A2B which will be our first model featuring ternary weight quantization.
We at
KV1 2.6B is near the midpoint of training, going well so far, its going to be our most agentic model yet.
We have released Klein Code Bench klein-ml/klein-code-bench, a benchmark testing whether models can build complete projects from scratch. It contains a easy, intermediate, hard and max subset.
Here are some benchmarks of the current KV1 1.2B
It retains 75.8% of FP16 intelligence.
We are also announcing that we at
- 2 replies