6 Commits

Include renames

Author	SHA1	Message	Date
Benjamin Greene	998dbd18c4	fix bug -> load_in_8bit and load_in_4bit were misnamed	2025-10-12 22:28:57 -05:00
Benjamin Greene	a91740f670	split model loading configuration into a separate node, add quantization config	2025-10-12 16:59:51 -05:00
Ben Greeneandtimkhronos	a8536dd124	Release 1.2.0 (#19) ... * add device map override functionality * fix syntax * update readme * Edit inference file so it keeps memory reserved * prepare release branch * make it so that the model is optionally unloaded between generations * remove newline * update assets and example workflow * update pyproject * reload the model if settings have changed; use model if it's already … (#16) * reload the model if settings have changed; use model if it's already loaded even if keep_model_in_memory is false * update readme * prepare relase 1.2.0 * Add moe drop tokens (#18) * moe_drop_tokens option * log kwargs, change readme * make moe_drop_tokens the default * edit readme --------- Co-authored-by: timkhronos <timkhronos@gmail.com>	2025-10-12 10:15:54 -05:00
Ben Greeneandtimkhronos	980a2f9334	Release 1.1.0 (#14) ... * add device map override functionality * fix syntax * update readme * Edit inference file so it keeps memory reserved * prepare release branch * make it so that the model is optionally unloaded between generations * remove newline * update assets and example workflow --------- Co-authored-by: timkhronos <timkhronos@gmail.com>	2025-10-11 20:09:04 -05:00
Benjamin Greene	891afde515	fix bug in image output, fix bug where parameters were not being passed	2025-10-06 23:38:12 -05:00
Benjamin Greene	511f7898dd	initial commit	2025-10-06 17:12:52 -05:00