Hugging Face's logo
Boning Cui's picture
šŸ—ļø Building on HF

Boning Cui

Bc-AI
213 20 84
webxos's profile picture 7p3k's profile picture dongxiat's profile picture
Ā·

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 šŸ‡¦šŸ‡ŗ (QLD Btw)

Recent Activity

repliedto SeaWolf-AI's post about 3 hours ago
We pretrained a 325M language model from zero on an inference-only NPU The accepted view is that inference-only NPUs cannot train, let alone pretrain a language model from scratch. We put that view to a direct test on the Rebellions ATOM-Max, a commercially available Korean NPU released in 2025 and designed for inference. We built our own training loop that runs backpropagation on the chip itself. Starting from random initialization, we pretrained VKORE-325M-NPU-Base, a 325.6M parameter model, on 5 billion byte tokens of FineWeb-Edu. The run took 76,292 steps over about four days and finished without a single divergence. No pretrained weights were used. To make the comparison fair, we trained the same model on a B200 GPU with identical initialization, data and learning-rate schedule. On 1,024 windows of text that neither model ever saw, the NPU reached a loss of 0.7993 and the GPU 0.7994. The window-by-window difference is -0.0001, well inside the noise. The two models are indistinguishable. This is seven times larger than our first NPU model, VKORE-46M, and the first time this hardware has carried a real pretraining run to GPU quality. Please note that the hardware alone does not make this possible: the NPU and its standard software are built for inference, and training on it depends on our own training stack and stability technique, which are developed in house and under patent application. Buying the chip does not by itself enable training. Both sets of weights and the evaluation script are public, so anyone can verify the result in minutes. šŸ“„ Technical report: https://huggingface.co/blog/FINAL-Bench/pretraining-a-325m-language-model-from-zero-on-an šŸ¤— Models: https://huggingface.co/FINAL-Bench/VKORE-325M-NPU-Base #NPU #Rebellions #Pretraining #VKORE
repliedto Banaxi-Tech's post about 5 hours ago
BananaMind is in the google situation before argon right now, right?
repliedto Banaxi-Tech's post about 7 hours ago
BananaMind is in the google situation before argon right now, right?
View all activity

Organizations

Gradio-Blocks-Party's profile picture Hugging Face Discord Community's profile picture None yet's profile picture Smilyai labs's profile picture XORTRON - Criminal Computing's profile picture Agents-MCP-Hackathon's profile picture Join Secret x Hugging Face's profile picture Hugging Science's profile picture MCP-1st-Birthday's profile picture Unsloth Jobs Explorers's profile picture Smilyai Mochiva Team's profile picture BananaMind Model Previewers's profile picture BananaMind AI's profile picture Grace Laboratories @ Smilyai Labs's profile picture Smilyai-labs-beta-testers's profile picture BananaMind Research Community's profile picture Small Language Model Consortium's profile picture Novi AI's profile picture basically experimental's profile picture basically AI's profile picture saicr's profile picture SAICR Join Requests's profile picture Smilyai Harbour AI Safety Team's profile picture VOID's profile picture Smilyai Project Prism's profile picture Refract AI Labs's profile picture RuVi-AI's profile picture Hugging Archive's profile picture Orion T3 Previewers's profile picture KV1 Early Access Program's profile picture Klein ML's profile picture HyperSLM's profile picture OpenModel Labs's profile picture