mrq a5c21d65d2 added automatically loading default YAML if --yaml is not profided (although I think it already does this by using defaults), default YAML will use local backend + deepspeed inferencing for speedups		2024-06-19 18:49:39 -05:00
..
emb
engines
ext
models	added automatically loading default YAML if --yaml is not profided (although I think it already does this by using defaults), default YAML will use local backend + deepspeed inferencing for speedups	2024-06-19 18:49:39 -05:00
utils	added automagic offloading models to GPU then CPU when theyre done during inference	2024-06-19 17:01:05 -05:00
__init__.py
__main__.py	fixed it breaking on subsequent utterances through the web UI from latents being on the CPU	2024-06-19 18:26:15 -05:00
config.py	added automatically loading default YAML if --yaml is not profided (although I think it already does this by using defaults), default YAML will use local backend + deepspeed inferencing for speedups	2024-06-19 18:49:39 -05:00
data.py
export.py
inference.py	added automatically loading default YAML if --yaml is not profided (although I think it already does this by using defaults), default YAML will use local backend + deepspeed inferencing for speedups	2024-06-19 18:49:39 -05:00
plot.py
samplers.py
tokenizer.py	semblance of documentation, automagic model downloading, a little saner inference results folder	2024-06-19 10:08:14 -05:00
train.py	added automagic offloading models to GPU then CPU when theyre done during inference	2024-06-19 17:01:05 -05:00
webui.py	fixed it breaking on subsequent utterances through the web UI from latents being on the CPU	2024-06-19 18:26:15 -05:00