Felladrin/Minueza-3-95M-Base
Text Generation • 94.7M • Updated • 105 • 3
Victor Nogueira
Felladrin
AI & ML interests
Models to run in the web browser
Recent Activity
updated a model about 1 hour ago
Felladrin/Minueza-3-95M-Base published a model about 1 hour ago
Felladrin/Minueza-3-95M-RP updated a model about 1 hour ago
Felladrin/Minueza-3-95M-RPOrganizations
updated a
model about 1 hour ago
published a
model about 1 hour ago
updated a
model about 1 hour ago
updated a
model about 9 hours ago
published a
model about 9 hours ago
updated a
Space about 15 hours ago
liked 4
Spaces 1 day ago
WritingBench
🏆
22
A Comprehensive Benchmark for Generative Writing
Agent Memory Leaderboard
🧠
716
Unified memory evaluation · Results expected August 12.
Music Arena Leaderboard
🎵
98
AI Music Arena & Leaderboard (Suno, Udio, Google, Meta, +)
Video Generation Leaderboard
📊
217
Text to Video and Image to Video Arena & Leaderboard
updated a
collection 1 day ago
updated a
model 1 day ago
published a
model 1 day ago
liked a
model 2 days ago
published a
model 3 days ago
updated a
collection 3 days ago
liked a
model 3 days ago
posted an update 3 days ago
Post
4055
I've open-sourced the trainer I've been using to build tiny language models from scratch, together with the 95M base model I trained with it.
The trainer runs on Deno (https://deno.com, cross-platform), trains on WebGPU, and it writes GGUF directly. No Python/PyTorch. The weights live in a GGUF file from the first step to the last, so every checkpoint is already something llama.cpp can load.
The model is Felladrin/Minueza-3-95M-Base: 94.7M parameters, 1.95B tokens seen, 8192 context.
And here’s the repository on GitHub: https://github.com/felladrin/gguf-trainer
Here on Hugging Face, I published the optimizer state next to the weights, so you can continue the pretraining instead of starting over.
Or start your own from nothing:
And the docs are written for coding agents, so you can point your agent of choice at the GitHub repo and have it drive the whole pipeline.
The trainer runs on Deno (https://deno.com, cross-platform), trains on WebGPU, and it writes GGUF directly. No Python/PyTorch. The weights live in a GGUF file from the first step to the last, so every checkpoint is already something llama.cpp can load.
The model is Felladrin/Minueza-3-95M-Base: 94.7M parameters, 1.95B tokens seen, 8192 context.
And here’s the repository on GitHub: https://github.com/felladrin/gguf-trainer
Here on Hugging Face, I published the optimizer state next to the weights, so you can continue the pretraining instead of starting over.
Or start your own from nothing:
deno run -A cli.ts demo trains a tiny one end to end in under a minute.And the docs are written for coding agents, so you can point your agent of choice at the GitHub repo and have it drive the whole pipeline.
- 36 replies
updated a
model 4 days ago
published a
model 4 days ago