Instructions to use Arkana08/B-NIMITA-L3-8B-v0.02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Arkana08/B-NIMITA-L3-8B-v0.02 with Transformers:

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

pipe = pipeline("text-generation", model="Arkana08/B-NIMITA-L3-8B-v0.02")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Arkana08/B-NIMITA-L3-8B-v0.02")
model = AutoModelForCausalLM.from_pretrained("Arkana08/B-NIMITA-L3-8B-v0.02", device_map="auto")
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 Arkana08/B-NIMITA-L3-8B-v0.02 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Arkana08/B-NIMITA-L3-8B-v0.02"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arkana08/B-NIMITA-L3-8B-v0.02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Arkana08/B-NIMITA-L3-8B-v0.02

SGLang

How to use Arkana08/B-NIMITA-L3-8B-v0.02 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 "Arkana08/B-NIMITA-L3-8B-v0.02" \
    --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": "Arkana08/B-NIMITA-L3-8B-v0.02",
		"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 "Arkana08/B-NIMITA-L3-8B-v0.02" \
        --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": "Arkana08/B-NIMITA-L3-8B-v0.02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Arkana08/B-NIMITA-L3-8B-v0.02 with Docker Model Runner:
```
docker model run hf.co/Arkana08/B-NIMITA-L3-8B-v0.02
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

(GGUF) Thanks:

mradermacher

GGUF: mradermacher/B-NIMITA-L3-8B-v0.02-GGUF
imatrix GGUF: mradermacher/B-NIMITA-L3-8B-v0.02-i1-GGUF

HumanBoiii

GGUF: HumanBoiii/B-NIMITA-L3-8B-v0.02-Q4_K_M-GGUF

B-NIMITA is an AI model designed to bring role-playing scenarios to life with emotional depth and rich storytelling. At its core is NIHAPPY, providing a solid narrative foundation and contextual consistency. This is enhanced by Mythorica, which adds vivid emotional arcs and expressive dialogue, and V-Blackroot, ensuring character consistency and subtle adaptability. This combination allows B-NIMITA to deliver dynamic, engaging interactions that feel natural and immersive. Model has 130k context.

Recomended ST Presets:
ChaoticNeutrals - Domain Fusion Presets
Virt-io - SillyTavern-Presets
Arkana08 - SillyTavern-Presets

output-model-directory

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Arkana08/NIHAPPY-L3.1-8B-v0.09 as a base.

Models Merged

The following models were included in the merge:

Configuration

Primary Model: NIHAPPY (base) - Balancing core narrative flow and contextual awareness. Additional Models:
Mythorica - Enhanced expressive flair, strong emotional arcs, detailed dialogue.
V-Blackroot - Precise focus on character consistency, subtle emotional undertones, adaptability in scene development.

The following YAML configuration was used to produce this model:

models:
  - model: Arkana08/Mythorica-L3-8B
    parameters:
      weight: 0.4
      density: 0.6
  - model: Arkana08/NIHAPPY-L3.1-8B-v0.09
    parameters:
      weight: 0.35
      density: 0.7
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
    parameters:
      weight: 0.25
      density: 0.55
merge_method: dare_ties
base_model: Arkana08/NIHAPPY-L3.1-8B-v0.09
parameters:
  int8_mask: true
dtype: bfloat16