Instructions to use Novi-AI/Novi-Mini-Base-Preview-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Novi-AI/Novi-Mini-Base-Preview-1 with Transformers:

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

pipe = pipeline("text-generation", model="Novi-AI/Novi-Mini-Base-Preview-1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Novi-AI/Novi-Mini-Base-Preview-1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Novi-AI/Novi-Mini-Base-Preview-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Novi-AI/Novi-Mini-Base-Preview-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Novi-AI/Novi-Mini-Base-Preview-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Novi-AI/Novi-Mini-Base-Preview-1

SGLang

How to use Novi-AI/Novi-Mini-Base-Preview-1 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 "Novi-AI/Novi-Mini-Base-Preview-1" \
    --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": "Novi-AI/Novi-Mini-Base-Preview-1",
		"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 "Novi-AI/Novi-Mini-Base-Preview-1" \
        --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": "Novi-AI/Novi-Mini-Base-Preview-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Novi-AI/Novi-Mini-Base-Preview-1 with Docker Model Runner:
```
docker model run hf.co/Novi-AI/Novi-Mini-Base-Preview-1
```

GGUFGuy commited on about 5 hours ago

Commit

35c4fb3

verified ·

1 Parent(s): dc227a7

Create README.md

Browse files

Files changed (1) hide show

README.md +109 -0

README.md ADDED Viewed

	@@ -0,0 +1,109 @@

+---
+language:
+- en
+license: apache-2.0
+tags:
+- novi-ai
+- language-model
+- pretrained-model
+- preview
+- small-language-model
+- bananamind-2-style
+- causal-lm
+- base-model
+- pretrained-from-scratch
+datasets:
+- HuggingFaceTB/smollm-corpus
+- mlfoundations/dclm-baseline-1.0
+- HuggingFaceTB/finemath
+- nvidia/OpenMathInstruct-2
+- HuggingFaceTB/smoltalk
+---
+# Novi Mini Base Preview !
+**An early preview of Novi Mini Base by Novi AI.**
+Novi Mini Base is a compact language model pretraining project featuring a **BananaMind 2-style architecture**, using a downscaled Cagliostro v3 design as its architectural basis.
+This repository contains a preview build from the ongoing pretraining run.
+## Model Information
+| Property | Details |
+|---|---|
+| Model name | Novi Mini Base |
+| Organization | Novi AI |
+| Model type | Causal Language Model |
+| Architecture style | BananaMind 2-style |
+| Architectural basis | Downscaled Cagliostro v3 |
+| Parameters | Approximately 10M |
+| Tokenizer | Byte-level BPE |
+| Vocabulary size | 8,192 |
+| Context length | 2,048 tokens |
+| Training objective | Next-token prediction |
+| Training tokens target | 15 billion |
+| Training schedule | Stable phase + cosine cooldown |
+## Training Progress
+This preview corresponds to checkpoint **168000**.
+| Metric | Value |
+|---|---:|
+| Current checkpoint | 168,000 |
+| Total planned steps | 457,764 |
+| Overall progress | 36.70% |
+| Stable-phase progress | 43.18% |
+Training is ongoing. The final model may differ from this preview.
+## Architecture
+Novi Mini Base follows a **BananaMind 2-style architecture**.
+Its architectural basis is a scaled-down Cagliostro v3 design, retaining the intended architectural approach while reducing model size for a compact training configuration.
+## Intended Use
+This is an experimental pretrained model intended for:
+- Language-model experimentation.
+- Fine-tuning experiments.
+- Small-model research.
+- Architecture evaluation.
+- Testing lightweight language models.
+This preview is not intended to be treated as a finished production model.
+## Loading the Model
+The model uses a custom architecture. Loading it may require the corresponding Novi Mini Base modeling and configuration files.
+Use trusted model code only.
+## Training
+Novi Mini Base is being pretrained on a planned dataset mixture totaling approximately **15 billion training tokens**.
+The training schedule consists of:
+1. Stable training phase.
+2. Cosine learning-rate cooldown phase.
+The final training target is 457,764 steps.
+## Project
+Developed by **Novi AI**.
+- Main model: https://huggingface.co/Novi-AI/Novi-Mini-Base
+- Checkpoints: https://huggingface.co/Novi-AI/Novi-Mini-Base-Checkpoints
+## Disclaimer
+This repository contains an intermediate training preview. Performance, capabilities, and output quality are not representative of the final model.
+The model is experimental and may produce inaccurate, incomplete, or nonsensical outputs.
+*Novi AI 2026 — Project Kairo*