Maple-Preview
deepgrove · Kit
A 20B ternary-weight reasoning model that activates about 1B parameters per token. Built for fast on-device use, with a 5.31 GB checkpoint and 131,072 token co…
deepgrove · Kit
A 20B ternary-weight reasoning model that activates about 1B parameters per token. Built for fast on-device use, with a 5.31 GB checkpoint and 131,072 token co…
DedeProGames · Kit
Continues English text with a tiny 65M-parameter decoder-only model trained on 80B tokens. For learners and researchers who want a small transformers model to…
MineAITechnology · Kit
A 124M-parameter GPT-2-style language model trained from scratch in JAX and Flax, with ONNX files for CPU use. It suits students and researchers who study smal…
BlinkDL · Kit
Pure RNN text-generation base models for chat, reasoning and tool calls, meant as a starting point for post-training and fine-tuning. Covers eight languages, f…
MineAITechnology · Kit
A small 355M English chat model from MineAI Technology that follows a simple User and Assistant format. A research-grade model that stops cleanly and writes sh…