MLewd series
Collection
Lewd models, made for ERP, trying to uncensor the maximum. • 12 items • Updated • 57
How to use Undi95/MLewd-L2-13B-v2-2 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Undi95/MLewd-L2-13B-v2-2") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Undi95/MLewd-L2-13B-v2-2")
model = AutoModelForCausalLM.from_pretrained("Undi95/MLewd-L2-13B-v2-2")How to use Undi95/MLewd-L2-13B-v2-2 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/MLewd-L2-13B-v2-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Undi95/MLewd-L2-13B-v2-2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Undi95/MLewd-L2-13B-v2-2
How to use Undi95/MLewd-L2-13B-v2-2 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Undi95/MLewd-L2-13B-v2-2" \
--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": "Undi95/MLewd-L2-13B-v2-2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "Undi95/MLewd-L2-13B-v2-2" \
--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": "Undi95/MLewd-L2-13B-v2-2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Undi95/MLewd-L2-13B-v2-2 with Docker Model Runner:
docker model run hf.co/Undi95/MLewd-L2-13B-v2-2
THIS MODEL IS MADE FOR LEWD
SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
Some topic that was censored in v2 (if not in instruction) isn't anymore in v2.2, try it!
[UPDATE SOON] V2.3 will use Slerpeno and ditch Stheno Inverted for even more spicyness, be ready!
This repo contains fp16 files of MLewd-L2-13B-v2-2, very hot and lewd model based on ReMM (SLERP).
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Special thanks to Sushi and Miko ♥