Instructions to use karyavirtual/novai-base-102m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use karyavirtual/novai-base-102m with Transformers:

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

pipe = pipeline("text-generation", model="karyavirtual/novai-base-102m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("karyavirtual/novai-base-102m")
model = AutoModelForCausalLM.from_pretrained("karyavirtual/novai-base-102m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use karyavirtual/novai-base-102m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "karyavirtual/novai-base-102m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "karyavirtual/novai-base-102m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/karyavirtual/novai-base-102m

SGLang

How to use karyavirtual/novai-base-102m 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 "karyavirtual/novai-base-102m" \
    --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": "karyavirtual/novai-base-102m",
		"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 "karyavirtual/novai-base-102m" \
        --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": "karyavirtual/novai-base-102m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use karyavirtual/novai-base-102m with Docker Model Runner:
```
docker model run hf.co/karyavirtual/novai-base-102m
```

NovAI Base 102M

NovAI Base 102M is an Indonesian-language causal language model developed by KaryaVirtual.

Created by: Nova Novriansyah, MSc, MBA

Model Details

Parameters: 102,558,240 (~102.6M)
Architecture: Llama-style decoder-only Transformer
Layers: 12
Hidden size: 720
Intermediate size: 1,920
Attention heads: 12
KV heads: 4
Vocabulary size: 50,257
Context length: 1,024 tokens
Tokenizer: GPT-2 tokenizer

Pretraining

The model was initialized with newly created model weights and pretrained on approximately 2 billion Indonesian-language tokens.

Training hardware:

NVIDIA A100 40GB

Dataset

The training corpus was prepared from HuggingFace FineWeb-2, using the Indonesian Latin (ind_Latn) subset.

Approximately:

2 billion training tokens
10 million validation tokens

The original dataset is not redistributed with this repository.

Users should refer to the upstream dataset documentation, license, and terms.

Source Repository

Technical documentation and supporting resources:

https://github.com/novrian6/novai

Training

The model was pretrained using causal language modeling.

Training tokens: ~2 billion
Validation tokens: ~10 million
Training steps: 15,259

Full pretraining logs and training source code are available in the project repository: https://github.com/novrian6/novai

Important

This model is not a fine-tuned copy of Llama, GPT, Claude, Gemini, or another pretrained foundation model.

The architecture uses the Llama implementation available through Hugging Face Transformers, while the model weights were newly initialized and pretrained separately for NovAI.

Training Evidence

The documented training run completed at:

15,259 / 15,259 steps

Training loss:

1.7229

Validation loss:

1.7012

Approximate training tokens:

2,000,027,648

Tokenizer

The model uses the GPT-2 tokenizer with a vocabulary size of 50,257 tokens.

Tokenizer: https://huggingface.co/openai-community/gpt2

Intended Use

NovAI Base 102M is intended for:

Indonesian NLP research
language-model experimentation
downstream fine-tuning
local inference experimentation
educational and research purposes

Limitations

NovAI Base 102M is a relatively small language model and should not be compared directly with substantially larger commercial or open-weight foundation models.

The model may generate incorrect, repetitive, biased, or factually unreliable content.

This repository contains the base pretrained model and is not an instruction-tuned conversational model.

License

The NovAI Base 102M model weights are released under the Apache License 2.0.

The training dataset, tokenizer, and third-party software remain subject to their respective licenses and terms.

Attribution

Model: NovAI Base 102M
Developer: KaryaVirtual
Author: Nova Novriansyah, MSc, MBA

Website: https://karyavirtual.com/

Downloads last month: 217

Safetensors

Model size

0.1B params

Tensor type

F32

karyavirtual
/

novai-base-102m