mrq 31785f4eeb actually don't default to compute split losses, test bitnet model doesn't seem to be doing things right (despite debug printouts showing theyre roughly the same logit/loss sequences, could just be bitnet linears being not up to par on actual models)		2024-06-01 09:12:51 -05:00
..
emb	DAC just doesn't work well enough......	2024-05-25 11:07:52 -05:00
engines	nan loss detection (should have added it earlier), loss scaling for local backend + fp16	2024-05-11 22:23:29 -05:00
ext	backwards compat for old YAMLs with models, option to set flash attention 2 for Llama (and derivatives), included syncdoth/RetNets torchscale retnet for shits and grins, etc.	2024-04-16 10:02:31 -05:00
models	added model config option to set KV head count for MQA/GQA instead of MHA for llama-based models (i think its very negligible both ways on such a small model size)	2024-05-31 19:32:37 -05:00
utils	some cleanup	2024-05-25 17:46:52 -05:00
__init__.py	Rewrite init	2023-08-02 21:53:35 +00:00
__main__.py	deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things	2024-04-15 19:54:32 -05:00
config.py	actually don't default to compute split losses, test bitnet model doesn't seem to be doing things right (despite debug printouts showing theyre roughly the same logit/loss sequences, could just be bitnet linears being not up to par on actual models)	2024-06-01 09:12:51 -05:00
data.py	DAC just doesn't work well enough......	2024-05-25 11:07:52 -05:00
export.py	cleanup, use deepspeed inferencing pathway if requested	2023-10-09 15:24:04 -05:00
inference.py	DAC just doesn't work well enough......	2024-05-25 11:07:52 -05:00
plot.py	deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things	2024-04-15 19:54:32 -05:00
samplers.py	separated samplers into its own file, don't bother copying the logits back to the GPU after sampling, it's not necessary	2023-10-11 12:25:31 -05:00
train.py	nevermind it breaks training	2024-05-25 18:03:43 -05:00
webui.py	backwards compat for old YAMLs with models, option to set flash attention 2 for Llama (and derivatives), included syncdoth/RetNets torchscale retnet for shits and grins, etc.	2024-04-16 10:02:31 -05:00