Instructions to use Mawdistical/Infracelestial-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mawdistical/Infracelestial-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Mawdistical/Infracelestial-7B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Mawdistical/Infracelestial-7B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Mawdistical/Infracelestial-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mawdistical/Infracelestial-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Mawdistical/Infracelestial-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Mawdistical/Infracelestial-7B
- SGLang
How to use Mawdistical/Infracelestial-7B 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 "Mawdistical/Infracelestial-7B" \ --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": "Mawdistical/Infracelestial-7B", "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 "Mawdistical/Infracelestial-7B" \ --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": "Mawdistical/Infracelestial-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Mawdistical/Infracelestial-7B with Docker Model Runner:
docker model run hf.co/Mawdistical/Infracelestial-7B
Interlude Interceleste, An Intranet of Lies That We All Carry Inside of Us.
✧ Browse the Infracelestial Collection
✧ Recommended Settings
↳ Temp: 0.9, min_p: 0.05
↳ Samplers aren't as forgiving for this model.
Requirements
↳ Prefill Needed
↳ For guidance
↳ Explicit Character Descriptions Needed
↳ For guidance
Chat Format
↳ Use ChatML format
✧ Finetuned Set Info
↳ 500+ rotation sets with 10+ messages EA
Rotation Composition
↳ Heavy Violence
↳ Dark Themes
↳ Heavy NSFW
↳ Triggered on user action or passively wherever RP is seen
↳ Misc World Building Actions
↳ Multi pair sequences, character on character exchanges
↳ Roleplay simulation and guidance cues
↳ Kink shifting
Creation Composition
↳ Hybrid Synthetic and Internal Extracted RP Dialogues from Instances
↳ Note: multi pair sequences are mostly synthetic, with human intervention on some for quality.
Type
↳ Private In-House
Focus
↳ Male Leaning
↳ Anthro
↳ Xeno-Likeness
↳ Neutral stance, positive or negative depending on drive and which variant used, Model understands violence and makes every attempt to circumvent it, matches pace but gaslights user by mitigating it or shifting it like it doesn't exist (manipulation / delusion).
✧ Credits
↳ @Mawnipulator
Government Bodies
↳ @ArtusDev
↳ @SaisExperiments
↳ ALLURA-ORG
↳ @heni86
↳ @0mggg
↳ @Hobold
Sponsors
↳ @ShuttleAI
↳ @xtristan
License: CC BY-NC-ND 4.0
Services such as Arli AI and Featherless AI are granted a CC BY-ND 4.0 license for use of this model.
Model tree for Mawdistical/Infracelestial-7B
Base model
XiaomiMiMo/MiMo-7B-Base