Modelpublic

MagistrTheOne/NULLXES-L-TEX-20B-Genesis-v0.1

sourceHugging Faceotherupdated 2mo agoView on Hugging Face

0likes17downloads

Model Card

NULLXES-LÆTEX-20B-Genesis-v0.1

Weight Genesis scaffold of the NULLXES-LÆTEX Stage2 dense proxy (~18.8B params, A35B-compatible width).

Developed by NULLXES · nullxesdai.online · Hub: MagistrTheOne

Status: research brick / architectural checkpoint. Not a chat model. Random muP-init weights — expect nonsense generations until Stage2 train. Next rework / first trained weights target: August 2026.

What this is

—Own architecture: LatexForCausalLM (model_type=latex), NHAT hybrid attention
—Shape: L=24, dmodel=8192, GQA 64/8, dff=22016 → ~18.757B
—Tokenizer: NULLXES-L-TEX-Tokenizer-v0.2 (131072 Unigram, full fill)
—Init: muP + DeepNorm residual scaling, bf16 sharded safetensors
—Intended path: Stage2 pretrain → A35B depth expand → future 480B-A35B MoE

What this is NOT

—Not instruct / not SFT / not a Digital Employee personality
—Not trained language competence (identity QA will fail on purpose)
—Not distilled from Qwen / Llama / Mistral / DeepSeek / GLM
—Not a replacement for 100M Stage0a (that one is identity-trained)

Load

python

import torch
from transformers import AutoModelForCausalLM, AutoConfig

repo = "MagistrTheOne/NULLXES-L-TEX-20B-Genesis-v0.1"
config = AutoConfig.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo, trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="auto"
)

Roadmap

When	Milestone
now	Genesis v0.1 (this repo)
next week	Stage2 ZeRO-3 smoke + ~100M tokens mid-eval on RTX PRO 6000
Aug 2026	First trained 20B weights / card refresh
later	A35B dense → 480B-A35B MoE (cluster)

Contact

NULLXES · @MagistrTheOne · ceo@nullxes.com