uncensored-tts
Collection
early checkpoints of morpheus - newest is the highest up • 1 item • Updated • 3
How to use MrDragonFox/mOrpheus_3B-1Base_early_preview-v1-25000 with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MrDragonFox/mOrpheus_3B-1Base_early_preview-v1-25000 to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MrDragonFox/mOrpheus_3B-1Base_early_preview-v1-25000 to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for MrDragonFox/mOrpheus_3B-1Base_early_preview-v1-25000 to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="MrDragonFox/mOrpheus_3B-1Base_early_preview-v1-25000",
max_seq_length=2048,
)(m)orpheus t(i)t(t)s
finetune of orpheus on uncensored/ (un)alingned data to be able to generate more interresting sounds
speaker name is "baddy" - trained on base prob. final checkpoint for the time beeing
bug reports / recommendations please in the discord https://discord.gg/RUs3uzBdW3
training still under way
should do
laughs gasps sights panting grunting kissing noises and many more
pretty reliable .. way more in there but hard to know what exactly works till we have a later checkpoint
checkpoint v1 25000