Post
49
We need to make software where people can start using decision models.
🏗️ 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
reacted to mithulaartigala's post with 🔥 about 12 hours ago
We need to make software where people can start using decision models.
liked a dataset about 14 hours ago
ProCreations/Beam-Reasoning-TracesOrganizations
reacted to mithulaartigala's post with 🔥 about 12 hours ago
reacted to Banaxi-Tech's post with 😔 about 17 hours ago
Post
129
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
replied to Banaxi-Tech's post about 17 hours ago
@Banaxi-Tech wdym shocked you? Zap?
reacted to DedeProGames's post with 🚀🔥➕🧠🤝👀👍 1 day ago
replied to DedeProGames's post 1 day ago
or the internet bandwidth lol
reacted to DavidAU's post with 🚀❤️ 6 days ago
Post
6,914
TURBO-BRILLIANCE 50X - Qwen 3.8 27B, Qwen-Flash Next (120B) Reg and Ablit/Uncensored, NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
15 AI CONSTRUCTS, SOTA Models + Turbo Brilliance:
Each a precision engineered "consciousness" to help you in every task, using fewer tokens and generating better answers.
This model has significant internal upgrades under user control that are "on the fly" (you set in your prompt(s) and/or API).
Each mode / construct reduces over all token usage and increases answer quality...
Please read this model card carefully to get the most from it - including all the reasoning and instruct modes (27+27+9 xhigh) that feature model suggestions ("context help") for all use cases.
The Turbo Brilliance system will begin appearing in other model sizes/types shortly (IE: Qwen, Gemma, Mistral, GLM, Llama, ... including our strongest fine tunes too). The "rollout" is now in progress...
Qwen-Flash-Next 120B, and run on 12GB GPU too (special project) at high speed, with RSQ-RCO BF16 level quants :
REG Version:
DavidAU/Qwen3.8-Flash-Next-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
Abliterated/Uncensored:
DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB: (2 bit, QAT, at close to BF16 performance , only 22GB!)
DavidAU/NVIDIA-Nemotron-3.5-Bolt-Turbo-Brilliance-50x-74B-A9B-24GB-GGUF
Qwen 3.8, 27B version:
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
PS: Qwen Next, LFM2.5 24B-A2B, Qwen 3.6 35B-A3B and others in testing now / coming soon.
COLLECTION:
https://huggingface.co/collections/DavidAU/turbo-brilliance-ai-constructs-50x-reasoning-instruct
Please see our support page for breakdown of models (sort), info on projects and a lot more information:
DavidAU/support
15 AI CONSTRUCTS, SOTA Models + Turbo Brilliance:
Each a precision engineered "consciousness" to help you in every task, using fewer tokens and generating better answers.
This model has significant internal upgrades under user control that are "on the fly" (you set in your prompt(s) and/or API).
Each mode / construct reduces over all token usage and increases answer quality...
Please read this model card carefully to get the most from it - including all the reasoning and instruct modes (27+27+9 xhigh) that feature model suggestions ("context help") for all use cases.
The Turbo Brilliance system will begin appearing in other model sizes/types shortly (IE: Qwen, Gemma, Mistral, GLM, Llama, ... including our strongest fine tunes too). The "rollout" is now in progress...
Qwen-Flash-Next 120B, and run on 12GB GPU too (special project) at high speed, with RSQ-RCO BF16 level quants :
REG Version:
DavidAU/Qwen3.8-Flash-Next-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
Abliterated/Uncensored:
DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB: (2 bit, QAT, at close to BF16 performance , only 22GB!)
DavidAU/NVIDIA-Nemotron-3.5-Bolt-Turbo-Brilliance-50x-74B-A9B-24GB-GGUF
Qwen 3.8, 27B version:
DavidAU/Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF
PS: Qwen Next, LFM2.5 24B-A2B, Qwen 3.6 35B-A3B and others in testing now / coming soon.
COLLECTION:
https://huggingface.co/collections/DavidAU/turbo-brilliance-ai-constructs-50x-reasoning-instruct
Please see our support page for breakdown of models (sort), info on projects and a lot more information:
DavidAU/support
replied to Banaxi-Tech's post 6 days ago
A hat is cool a brain chip is uuuh weird
replied to Banaxi-Tech's post 7 days ago
well as long as its not in my brain im happy a hat or smth yes
replied to Banaxi-Tech's post 7 days ago
This comment has been hidden
replied to DedeProGames's post 7 days ago
Congrats!
reacted to DedeProGames's post with 🤯🚀🧠 7 days ago
Post
8,855
🚀 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