| .. |
|
emb
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
engines
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
ext
|
|
|
|
models
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
utils
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
__init__.py
|
|
|
|
__main__.py
|
added ability to specify attention backend for CLI and webui (because im tired of editing the yaml)
|
2024-08-26 19:33:51 -05:00 |
|
config.py
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
data.py
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
demo.py
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
export.py
|
added export option to convert Llama to MixtralMoE for another dumb experiment
|
2024-08-04 20:25:06 -05:00 |
|
inference.py
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
plot.py
|
|
|
|
samplers.py
|
possible speedup for samplers that require a list of previous tokens (the DRY sampler made me realize that I should copy the tolist() thing from the rep pen sampler for everything else)
|
2024-07-29 20:23:26 -05:00 |
|
train.py
|
moved prints to use logger, edited readme (fused_attn doesnt seem stable for training)
|
2024-08-29 13:27:16 -05:00 |
|
webui.py
|
added ability to specify attention backend for CLI and webui (because im tired of editing the yaml)
|
2024-08-26 19:33:51 -05:00 |
