Instructions to use Aobangaming/aoban-1-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aobangaming/aoban-1-base with Transformers:

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

pipe = pipeline("text-generation", model="Aobangaming/aoban-1-base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Aobangaming/aoban-1-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aobangaming/aoban-1-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aobangaming/aoban-1-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aobangaming/aoban-1-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aobangaming/aoban-1-base

SGLang

How to use Aobangaming/aoban-1-base 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 "Aobangaming/aoban-1-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aobangaming/aoban-1-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Aobangaming/aoban-1-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aobangaming/aoban-1-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aobangaming/aoban-1-base with Docker Model Runner:
```
docker model run hf.co/Aobangaming/aoban-1-base
```

Model Card for Aoban 1

Model Details

Aoban is a next generation text model designed for keeping context over long amounts of text.

Model creator: AobanZ

Model Description

Aoban utilizes FlashAttention and AdamW for performance and capability. Lightning is designed to provide quick, coherent outputs, improved with a larger size and weight.

Developed by: AobanZ
Model type: Transformer
Language(s) (NLP): English
License: MIT

Model Sources

Repository: https://huggingface.co/Aobangaming/aoban-1-base

Uses

Aoban is intended to be used for research, analysis and fine-tuning, general conversation, stories and other. It is not intended to be used for professional advice, real writing or any kind of heavy work as generated outputs may be incorrect.

Direct Use

Aoban can be used directly for text generation, experimentation, and conversational interactions. Users can provide text prompts and generate responses using the model's built-in language modeling capabilities. Direct use is primarily intended for research and experimentation. Outputs may be incomplete, inaccurate, repetitive, or unrelated to the input, and should be evaluated before being used for other purposes.

Downstream Use

This model can be fine tuned to a text continuer.

Out-of-Scope Use

Heavy Work may overload the model, which will cause corrupted outputs and/or misinformation. Please provide coherent, steady prompts as the model may not understand unfamiliar terms.

Bias, Risks, and Limitations

Aoban is designed to process english and conversational text ONLY and cannot be fined-tuned for any other uses(eg. Robotics). Aoban is prone to generate formal text.

Recommendations

We recommend users of Aoban to finetune the model on new text, and add necessary guardrails and precautions to prevent misuse.

How to Get Started with the Model

Use the code below to get started with the model.

import torch
from transformers import AutoModelForCausalLM
from tokenizers import Tokenizer
from huggingface_hub import hf_hub_download
import importlib.util

model_id = "Aobangaming/aoban-1-base"

path = hf_hub_download(model_id, "modeling_luna.py")
spec = importlib.util.spec_from_file_location("lightning", path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)

model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, ignore_mismatched_sizes=False
)
tokenizer = Tokenizer.from_file(
    hf_hub_download(model_id, "luna_tokenizer.json")
)

Generation(OPTIONAL)

response = module.generate_text(
    model,
    tokenizer,
    prompt,
    max_len=100,
    device=device,
    top_k=40,
    top_p=0.6,
    penalty=1.2,
    temperature=0.8,
)

Training Details

Training Data

Luna was trained on highly specialized, high quality english sentences.

Training Procedure

Luna was trained on an RTX 3050 GPU, using FlashAttention/SDPA and MHA. The model was trained on a large dataset. It was not trained on fine-tuning datasets since memory issues.

Training Results

Epoch	Average Loss	Perplexity
1/10	7.403553344	1641.808227539
2/10	6.424439240	616.734985352
3/10	5.926600045	374.877746582
4/10	5.413045830	224.313781738
5/10	4.846523407	127.297042847
6/10	4.230059040	68.721298218
7/10	3.576859904	35.761074066
8/10	3.068302144	21.505359650
9/10	2.610309639	13.603261948
10/10	1.846334972	6.336553097

Training Hyperparameters

Hyperparameter	Value	Comment
Precision	FP32
Optimizer	AdamW
Learning rate	4e-4
Batch size	32

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: RTX 3050 6GB
Hours used: 1.5
Cloud Provider: AobanLabs
Compute Region: Asia
Carbon Emitted: ~0.17 kg CO₂e

Technical Specifications

Model Architecture and Objective

Aoban uses a 8-layer causal Transformer with 384-dimensional hidden states and 6 attention heads, inherited from previous models. The architecture is based on the base architecture of "Aoban Lightning", which uses pre-layer normalization, causal scaled dot-product attention, a 4× expansion GELU feed-forward network, sinusoidal positional encoding, and untied input/output embeddings.

Hyperparameter	Value	Comment
Layers	8
D_MODEL	384
Attention Heads	6
Vocabulary	~75000	w/ 200 Sequence length

Downloads last month: -

Safetensors

Model size

71.9M params

Tensor type

F32

Dataset used to train Aobangaming/aoban-1-base

Paper for Aobangaming/aoban-1-base

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 61