Instructions to use divinetaco/aranea-ancilla-116b-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divinetaco/aranea-ancilla-116b-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="divinetaco/aranea-ancilla-116b-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("divinetaco/aranea-ancilla-116b-v1.0")
model = AutoModelForMultimodalLM.from_pretrained("divinetaco/aranea-ancilla-116b-v1.0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use divinetaco/aranea-ancilla-116b-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "divinetaco/aranea-ancilla-116b-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "divinetaco/aranea-ancilla-116b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/divinetaco/aranea-ancilla-116b-v1.0

SGLang

How to use divinetaco/aranea-ancilla-116b-v1.0 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 "divinetaco/aranea-ancilla-116b-v1.0" \
    --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": "divinetaco/aranea-ancilla-116b-v1.0",
		"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 "divinetaco/aranea-ancilla-116b-v1.0" \
        --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": "divinetaco/aranea-ancilla-116b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use divinetaco/aranea-ancilla-116b-v1.0 with Docker Model Runner:
```
docker model run hf.co/divinetaco/aranea-ancilla-116b-v1.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

aranea-ancilla-116b-v1.0

aka MiquMaid-v1-70B + interleaved WinterGoddess-1.4x-70B-L2

A mergekit frankenmerge based on NeverSleep/MiquMaid-v1-70B with interleaved layers of Sao10K/WinterGoddess-1.4x-70B-L2.
This was the top performing model from a series of merge experiments to create a highly coherant creative writing model.

Tests consisted of a series of private benchmarks and manual comparisons. A number of different base models, interleave models and layer offsets were compared.

Usable context ~32768
Recommended context ~16384

Non frankenstein miqu-1 finetunes generally outperform their frankenstein counterparts at very long contexts due to coherency loss.
As a rough suggestion I might suggest swapping out to either NeverSleep/MiquMaid-v1-70B or 152334H/miqu-1-70b-sf after 16k context.

Layers: 136

License

No license. Component models based on the Mistral AI Miqu-1 llama2 finetune that was released without license.

Interesting observations from benchmarking

10 layer interleave stride with a 20 layer interleave width consistently outperformed alternatives combinations.
Offsetting the interleaved model's first set of layers generally improved coherency. [14-30] reliably beat the [10-30] mergekit slice configuration for various combinations of models.
Quality of resulting merges can vary wildly. Whilst a merge of two strong models tends to produce a strong frankenstein model, this rule does not always hold true.

Quantizations

Exllamav2 quants will be available when bandwidth permits.

Downloads last month: 1

Safetensors

Model size

117B params

Tensor type

F16

Model tree for divinetaco/aranea-ancilla-116b-v1.0

152334H/miqu-1-70b-sf

NeverSleep/MiquMaid-v1-70B

Sao10K/WinterGoddess-1.4x-70B-L2

Merge model

this model

Quantizations

2 models