Instructions to use MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0

SGLang

How to use MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0 with Docker Model Runner:
```
docker model run hf.co/MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0
```

NULLXES-LÆTEX-100M-Stage0a-v0

First trained brain of the NULLXES-LÆTEX family (~102M params, dense NHAT).

Developed by NULLXES · nullxesdai.online · org on Hub via MagistrTheOne

What this is

Own architecture (LatexForCausalLM, model_type=latex)
Own tokenizer (NULLXES-LÆTEX v0.1, vocab export 131072, ~4k real Unigram pieces + unused pad)
Bootstrap pretrain on NULLXES identity + repo code corpus (~50M tokens)
Intended to answer as LÆTEX / NULLXES-LÆTEX, not as ChatGPT/Claude/Llama

What this is NOT

Not a general-purpose LLM
Not Chinchilla-scale pretrain (tiny corpus → heavy memorization / overfit)
Not the 7B genesis (separate architectural checkpoint)
Not distilled from Qwen/Llama/Mistral/DeepSeek

Load

import torch
from transformers import AutoModelForCausalLM, AutoConfig

# registers custom classes
repo = "MagistrTheOne/NULLXES-L-TEX-100M-Stage0a-v0"
config = AutoConfig.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo, trust_remote_code=True, torch_dtype=torch.bfloat16
)

Tokenizer artifacts ship in-repo (tokenizer.model, special_tokens.json). Prefer loading via the research package LatexTokenizer from the NULLXES-LÆTEX GitHub when doing local QA.

Identity

Correct self-name: NULLXES-LÆTEX (short: LÆTEX), built by NULLXES for Digital Employees.

Training note

Stage0a bootstrap: ~50M tokens, final train loss ~0.01 on a small identity/code mix. Treat as research brick #1, not production intelligence.

Downloads last month: 26

Safetensors

Model size

0.1B params

Tensor type

BF16