Post
6,149
BananaMind 3 is coming.
Biggest context in all SLMs with NSA.
10M, 50M, 150M, 400M.
And maybe, 1B.
Biggest context in all SLMs with NSA.
10M, 50M, 150M, 400M.
And maybe, 1B.
- 14 replies
Hoglet (Ash) PRO
Hoglet-33
AI & ML interests
Open source AI, datasets, non-attention based models, parameter efficiency, SLMs, AI for the betterment of humanity. Contact at ash@basicallyai.co
Recent Activity
liked a Space about 19 hours ago
juiceb0xc0de/BYOGGUF reacted to Banaxi-Tech's post with 🔥 about 21 hours ago
BananaMind 3 is coming.
Biggest context in all SLMs with NSA.
10M, 50M, 150M, 400M.
And maybe, 1B.Organizations
reacted to Banaxi-Tech's post with 🔥 about 21 hours ago
replied to Banaxi-Tech's post 1 day ago
oh ok, thank you @Banaxi-Tech
replied to Banaxi-Tech's post 2 days ago
lol, im hysterical right now
replied to Banaxi-Tech's post 2 days ago
i need to know
replied to Banaxi-Tech's post 2 days ago
@Bc-AI longer than ours?
reacted to Banaxi-Tech's post with 👀 2 days ago
Post
6,149
BananaMind 3 is coming.
Biggest context in all SLMs with NSA.
10M, 50M, 150M, 400M.
And maybe, 1B.
Biggest context in all SLMs with NSA.
10M, 50M, 150M, 400M.
And maybe, 1B.
- 14 replies
reacted to Banaxi-Tech's post with 🔥 2 days ago
Post
6,670
We've released the BananaMind/BETU-SLM-Leaderboard
Its so simple to use, it ranks models, and by one command add your own model to it.
It scores by Overall Index which is a weighted mix of Hellaswawg, ARC EASY, PIQA, Arithmark 3, Tiny Theory of Mind, and BananaMind Base Bench.
Its so simple to use, it ranks models, and by one command add your own model to it.
It scores by Overall Index which is a weighted mix of Hellaswawg, ARC EASY, PIQA, Arithmark 3, Tiny Theory of Mind, and BananaMind Base Bench.
- 1 reply
replied to Banaxi-Tech's post 2 days ago
More than Pebble 1.5? ours will be recurrent.
replied to DedeProGames's post 2 days ago
Can't wait!
reacted to DedeProGames's post with 🔥 2 days ago
Post
4,394
We are working on LFM3-1.7B-Ox, a compact model for repo-level programming, agentic coding, and tinkering.
- 2 replies
replied to their post 18 days ago
lol thanks man
reacted to their post with 😔❤️👀🔥 19 days ago
Post
3,963
I wish Hugging Face posts had polls...
- 6 replies
posted an update 19 days ago
Post
3,963
I wish Hugging Face posts had polls...
- 6 replies
reacted to Banaxi-Tech's post with 😔 23 days ago
Post
204
So... im on vacation for 5 more days and I just realized... my hotel doesent have a grounding port 😟 so my pc shocked me 3 times.
So no progress for 5 days... only me and this phone
So no progress for 5 days... only me and this phone
- 2 replies
reacted to DedeProGames's post with 🚀🔥 about 1 month ago
Post
8,945
🚀 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
replied to DedeProGames's post about 1 month ago
@DedeProGames Why those languages?