Instructions to use N-Bot-Int/MaidEllaA-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use N-Bot-Int/MaidEllaA-1B with Transformers:

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

pipe = pipeline("text-generation", model="N-Bot-Int/MaidEllaA-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("N-Bot-Int/MaidEllaA-1B")
model = AutoModelForCausalLM.from_pretrained("N-Bot-Int/MaidEllaA-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use N-Bot-Int/MaidEllaA-1B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/N-Bot-Int/MaidEllaA-1B

SGLang

How to use N-Bot-Int/MaidEllaA-1B 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 "N-Bot-Int/MaidEllaA-1B" \
    --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": "N-Bot-Int/MaidEllaA-1B",
		"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 "N-Bot-Int/MaidEllaA-1B" \
        --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": "N-Bot-Int/MaidEllaA-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use N-Bot-Int/MaidEllaA-1B with Docker Model Runner:
```
docker model run hf.co/N-Bot-Int/MaidEllaA-1B
```

MaidEllaA-1B / README.md

ItsMeDevRoland

Update README.md

5afb898 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

3.34 kB

	---
	base_model:
	- N-Bot-Int/MiniMaid-L3
	- N-Bot-Int/OpenElla-StoryWriter-TypeB
	library_name: transformers
	tags:
	- mergekit
	- merge
	- Uncensored
	- roleplay
	- conversational
	- text-generation-inference
	- transformers
	- llama
	license: agpl-3.0
	language:
	- en
	pipeline_tag: text-generation
	---
	### MaidEllaA-1B is Now officially released!
	This will be the last model for this month of april, There will be no more models until May since we're trying to pave a way for our Next targets! SEE YOU IN MAY!
	![image](https://cdn-uploads.huggingface.co/production/uploads/6633a73004501e16e7896b86/lTVmC7PMveCLIoIkBDT6Q.png)
	- Image generated by CHATGPT

	### MaidEllaA-1B, Mixed from Two Best 1B model, Forged to be the greatest 1B model we MADE!
	- Our pursuit at making THE BEST 1B model for RP has Yield us to produce MaidEllaA... Our brand new AI Model that aims to be the Next contender to the most
	Powerful 1B Model compared to its last predecessors, MiniMaid and OpenElla-StoryWriter. MaidEllaA combines our Two Best 1B Model(ie, MiniMaid-L3 and Storywriter-TypeB).
	Producing MaidEllaA!

	- This Model was made using MERGEKIT, with a conservative configuration of 0.5 density so Both model has a meaningful contribution without one model overpowering,
	or Overcontributing luckluster portion of the said parent model, The Model is trained using [SLERP](https://en.wikipedia.org/wiki/Slerp) method! (EXPERIMENTAL!)

	- On other Keynote, MaidEllaA-1B, Is NOW TRAINED On Kaggle!, with a goal of Making The BEST Smallest RP model that can be Run on any hardware!

	- The Model May OR MAY NOT INHERIT the Uncensored Nature of OpenElla-StoryWriter-TypeB, this is because MiniMaid-L3 has a weak Uncensorship SFT's which could
	Produce unwanted behaviors!

	### Models Merged
	The following models were included in the merge:
	* [N-Bot-Int/OpenElla-StoryWriter-TypeB](https://huggingface.co/N-Bot-Int/OpenElla-StoryWriter-TypeB)
	* [N-Bot-Int/MiniMaid-L3](https://huggingface.co/N-Bot-Int/MiniMaid-L3)
	wherein, both received a density of 0.5, ensuring the merged model, receives 50% from each

	### NOTICE
	- N-Bot-Int/MaidEllaA-1B is Our Brand New Powerful Model, If you ever encountered any issue, Want to commission us, or have any suggestions, please email us directly through
	[nexus.networkinteractives@gmail.com](mailto:nexus.networkinteractives@gmail.com)
	we value any reports, suggestions to how we improve future Model,
	Once again feel free to finetune the model to your likings, However please consider Adding this Page
	for CREDITS

	- Please handle the AI with Care and ethical considerations when FINETUNING this AI model. This is because of its UNCENSORED Nature(Or Lack thereof).
	- We are not responsible for what this model generates. Use it responsibly and legally. You downloaded it, you own what you do with it.

	### Footer
	- MaidEllaA-1B is
	- Developed by: N-Bot-Int
	- License: agpl 3.0

	(PLACEHOLDER BENCHMARK)

	- # Notice
	- For a Good Experience, Please use
	- (PLEASE CALIBRATE THE MODEL DEPENDING ON THE CHARACTER CARD YOU USE)

	- # Detail card:
	- Parameter
	- 1 Billion Parameters
	- (Please check your GPU Core, VRAM, CPU and RAM to see if you can comfortably run 1B models)

	- # Finetuning tool:
	- Mergekit
	- Fine-tuned Using:
	- Kaggle T4x2