SupraLabs/SupraElegans-500k开源了新模型

SupraLabs SupraLabs/SupraElegans-500k SupraLabs/SupraElegans-500k https://huggingface.co/SupraLabs/SupraElegans-500k

SupraLabs/SupraElegans-500k · Hugging Face Hugging Face (https://huggingface.co/) Models (https://huggingface.co/models) Datasets (https://huggingface.co/datasets) Spaces (https://huggingface.co/spaces) Buckets new (https://huggingface.co/storage) Docs (https://huggingface.co/docs) Enterprise (https://huggingface.co/enterprise) Pricing (https://huggingface.co/pricing) Website Tasks (https://huggingface.co/tasks) HuggingChat (https://huggingface.co/chat) Collections (https://huggingface.co/collections) Languages (https://huggingface.co/languages) Organizations (https://huggingface.co/organizations) Community Blog (https://huggingface.co/blog) Posts (https://huggingface.co/posts) Daily Papers (https://huggingface.co/papers) Hardware (https://huggingface.co/hardware) Learn (https://huggingface.co/learn) Discord (https://huggingface.co/join/discord) Forum (https://discuss.huggingface.co/) GitHub (https://github.com/huggingface) Solutions Team & Enterprise (https://huggingface.co/enterprise) Hugging Face PRO (https://huggingface.co/pro) Enterprise Support (https://huggingface.co/support) Inference Providers (https://huggingface.co/inference/models) Inference Endpoints (https://huggingface.co/inference-endpoints) Storage Buckets (https://huggingface.co/storage) Log In (https://huggingface.co/login) Sign Up (https://huggingface.co/join) (https://huggingface.co/SupraLabs) SupraLabs (https://huggingface.co/SupraLabs) / SupraElegans-500k (https://huggingface.co/SupraLabs/SupraElegans-500k) like 29 Follow SupraLabs 366 Text Generation (https://huggingface.co/models?pipeline_tag=text-generation) Safetensors (https://huggingface.co/models?library=safetensors) English (https://huggingface.co/models?language=en) supraelegans (https://huggingface.co/models?other=supraelegans) causal-lm (https://huggingface.co/models?other=causal-lm) recurrent (https://huggingface.co/models?other=recurrent) sparse (https://huggingface.co/models?other=sparse) experimental (https://huggingface.co/models?other=experimental) biologically-inspired (https://huggingface.co/models?other=biologically-inspired) custom_code (https://huggingface.co/models?other=custom_code) License: apache-2.0 Model card (https://huggingface.co/SupraLabs/SupraElegans-500k) Files Files and versions xet (https://huggingface.co/SupraLabs/SupraElegans-500k/tree/main) Community 4 (https://huggingface.co/SupraLabs/SupraElegans-500k/discussions) Copy to bucket new SupraElegans-500K (https://huggingface.co/SupraLabs/SupraElegans-500k#supraelegans-500k) Architecture (https://huggingface.co/SupraLabs/SupraElegans-500k#architecture) What this model is and isn't (https://huggingface.co/SupraLabs/SupraElegans-500k#what-this-model-is-and-isnt) Usage (https://huggingface.co/SupraLabs/SupraElegans-500k#usage) You must have modeling_supraelegans.py on the same folder as this code! (https://huggingface.co/SupraLabs/SupraElegans-500k#you-must-have-modeling_supraeleganspy-on-the-same-folder-as-this-code) Manual state control (https://huggingface.co/SupraLabs/SupraElegans-500k#manual-state-control) Benchmarks (https://huggingface.co/SupraLabs/SupraElegans-500k#benchmarks) Training (https://huggingface.co/SupraLabs/SupraElegans-500k#training) Limitations (https://huggingface.co/SupraLabs/SupraElegans-500k#limitations) License (https://huggingface.co/SupraLabs/SupraElegans-500k#license) (https://huggingface.co/SupraLabs/SupraElegans-500k#supraelegans-500k) SupraElegans-500K SupraElegans-500K is a ~500,000-parameter causal language model built around a sparse, signed, recurrent neural graph instead of a Transformer. It has no attention mechanism, no positional encoding, and no KV cache. Context is carried by a persistent per-neuron membrane potential that is updated token by token. The architecture is loosely inspired by ideas from the C. elegans nervous system: sparse connectivity, distinct neuron populations, excitatory/inhibitory signaling, and persisten