various bugfixes
94f5e41
-
accelerate
quickstart instructions for starting from runpod (#5)
-
934 Bytes
4bit quantized support (wip)
-
909 Bytes
WIP large refactor to make finetune script a little more manageable (#3)
-
935 Bytes
fix lora target module, require explicit flash attention, fix min logging steps, don't use adam8bit for int4, hash prepared datasets, support hf hub datasets
-
975 Bytes
quickstart instructions for starting from runpod (#5)
-
933 Bytes
fix lora target module, require explicit flash attention, fix min logging steps, don't use adam8bit for int4, hash prepared datasets, support hf hub datasets
-
978 Bytes
4bit quantized support (wip)
-
975 Bytes
quickstart instructions for starting from runpod (#5)
-
3.66 kB
quickstart instructions for starting from runpod (#5)
-
663 Bytes
various bugfixes
-
1.05 kB
add support for alpaca reflect training (#2)
