# Kitsun: Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/kitsuvp
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model

### [NeoLLM](https://savrn.com/models/neollm)

[Kitsun](https://savrn.com/model-publishers/kitsuvp)

NeoLLM is a 85.50 M parameter decoder-only language model trained from scratch on FineWeb-Edu with BF16 compute, completing training in approximately ~1h 16m on NVIDIA GeForce RTX 5090. It integrates a collection of recently published attention and normalization techniques into a single architecture, with the goal of studying how they interact during pretraining. The model is actively being developed and the current checkpoint represents an intermediate training state. NeoLLM is a decoder-only transformer with the following configuration: NeoLLM combines architecture modules, optional auxiliary objectives, and training-time optimizer/stability components from the following papers. Embedding…

Open weights apache-2.0 86M parameters 512 tokens

[View model](https://savrn.com/models/neollm)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-10-07.
- [Hugging Face profile](https://huggingface.co/KitsuVp)
- [How the hub is built](https://savrn.com/model-hub/methodology)