DedeProGames PRO
DedeProGames
AI & ML interests
Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher
Recent Activity
reacted to theirpost with 🤝 about 2 hours ago
@DavidAU is officialy humanslop reacted to theirpost with 👍 about 2 hours ago
@DavidAU is officialy humanslop reacted to theirpost with 🧠 about 2 hours ago
@DavidAU is officialy humanslopOrganizations
reacted to their post with 🤝👍🧠🔥 about 2 hours ago
updated a
dataset about 22 hours ago
updated 2
models 1 day ago
liked a
Space 1 day ago
replied to their post 1 day ago
Thanks for the suggestion! I ran the CPU benchmark and Portuguese-IFEval. The F16 GGUF scored 6.54% strict prompt accuracy and decoded at 65.5 tokens/s with llama.cpp, versus 10.8 tokens/s in PyTorch FP32. The chat template passed all 9 checks. I couldn’t finish the Q4_K_M quality run, so I don’t have a valid Q4 score yet.
replied to their post 3 days ago
Ent, e dificil ahcar aqui kkkkkk
liked a
model 3 days ago
liked a
Space 4 days ago
And me?
1
#1 opened 4 days ago
by DedeProGames
liked a
model 4 days ago
liked a
Space 4 days ago
replied to their post 5 days ago
Im from Brazil
reacted to their post with 🤯 5 days ago
Post
8,832
🚀 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