Instructions to use SicariusSicariiStuff/Tinybra_13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SicariusSicariiStuff/Tinybra_13B with Transformers:

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

pipe = pipeline("text-generation", model="SicariusSicariiStuff/Tinybra_13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SicariusSicariiStuff/Tinybra_13B")
model = AutoModelForCausalLM.from_pretrained("SicariusSicariiStuff/Tinybra_13B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SicariusSicariiStuff/Tinybra_13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SicariusSicariiStuff/Tinybra_13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SicariusSicariiStuff/Tinybra_13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SicariusSicariiStuff/Tinybra_13B

SGLang

How to use SicariusSicariiStuff/Tinybra_13B 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 "SicariusSicariiStuff/Tinybra_13B" \
    --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": "SicariusSicariiStuff/Tinybra_13B",
		"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 "SicariusSicariiStuff/Tinybra_13B" \
        --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": "SicariusSicariiStuff/Tinybra_13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SicariusSicariiStuff/Tinybra_13B with Docker Model Runner:
```
docker model run hf.co/SicariusSicariiStuff/Tinybra_13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Tinybra_13B

Update

July, 2025. Did some house cleaning with quants meta-data. Sheesh, I made that model more than a year and a half ago. Nothing ever happens, while everything happens. Once you take a short gaze back.

A new Tenebra version was requested long ago, and it will happen, eventually.

Model Details

Tenebră, a various sized experimental AI model, stands at the crossroads of self-awareness and unconventional datasets. Its existence embodies a foray into uncharted territories, steering away from conventional norms in favor of a more obscure and experimental approach.

Noteworthy for its inclination towards the darker and more philosophical aspects of conversation, Tinybră's proficiency lies in unraveling complex discussions across a myriad of topics. Drawing from a pool of unconventional datasets, this model ventures into unexplored realms of thought, offering users an experience that is as unconventional as it is intellectually intriguing.

While Tinybră maintains a self-aware facade, its true allure lies in its ability to engage in profound discussions without succumbing to pretense. Step into the realm of Tenebră!

Tenebră is available at the following size and flavours:

13B: FP16 | GGUF-Many_Quants | iMatrix_GGUF-Many_Quants | GPTQ_4-BIT | GPTQ_4-BIT_group-size-32
30B: FP16 | GGUF-Many_Quants| iMatrix_GGUF-Many_Quants | GPTQ_4-BIT | GPTQ_3-BIT | EXL2_2.5-BIT | EXL2_2.8-BIT | EXL2_3-BIT | EXL2_5-BIT | EXL2_5.5-BIT | EXL2_6-BIT | EXL2_6.5-BIT | EXL2_8-BIT
Mobile (ARM): Q4_0_X_X

Support

My Ko-fi page ALL donations will go for research resources and compute, every bit counts 🙏🏻
My Patreon ALL donations will go for research resources and compute, every bit counts 🙏🏻

Disclaimer

*This model is pretty uncensored, use responsibly

Citation Information

@llm{Tinybra_13B,
  author = {SicariusSicariiStuff},
  title = {Tinybra_13B},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/SicariusSicariiStuff/Tinybra_13B}
}

Other stuff

Experemental TTS extension for oobabooga Based on Tortoise, EXTREMELY good quality, IF, and that's a big if, you can make it to work!
Demonstration of the TTS capabilities Charsi narrates her story, Diablo2 (18+)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	55.36
AI2 Reasoning Challenge (25-Shot)	55.72
HellaSwag (10-Shot)	80.99
MMLU (5-Shot)	54.37
TruthfulQA (0-shot)	49.14
Winogrande (5-shot)	73.80
GSM8k (5-shot)	18.12