91 Commits

Author	SHA1	Message	Date
oobabooga	bba5b36d33	Don't import PEFT unless necessary	2024-09-03 19:40:53 -07:00
oobabooga	5223c009fe	Minor change after previous commit	2024-07-27 23:13:34 -07:00
oobabooga	7050bb880e	UI: make n_ctx/max_seq_len/truncation_length numbers rather than sliders	2024-07-27 23:11:53 -07:00
oobabooga	bd7cc4234d	Backend cleanup (#6025)	2024-05-21 13:32:02 -03:00
oobabooga	faf3bf2503	Perplexity evaluation: make UI events more robust (attempt)	2024-02-22 07:13:22 -08:00
ilya sheprut	4d14eb8b82	LoRA: Fix error "Attempting to unscale FP16 gradients" when training (#5268)	2024-01-17 17:11:49 -03:00
AstrisCantCode	b80e6365d0	Fix various bugs for LoRA training (#5161)	2024-01-03 20:42:20 -03:00
oobabooga	9992f7d8c0	Improve several log messages	2023-12-19 20:54:32 -08:00
oobabooga	131a5212ce	UI: update context upper limit to 200000	2023-12-04 15:48:34 -08:00
Julien Chaumond	a56ef2a942	make torch.load a bit safer (#4448)	2023-11-02 14:07:08 -03:00
oobabooga	262f8ae5bb	Use default gr.Dataframe for evaluation table	2023-10-27 06:49:14 -07:00
Abhilash Majumder	778a010df8	Intel Gpu support initialization (#4340)	2023-10-26 23:39:51 -03:00
adrianfiedler	4bc411332f	Fix broken links (#4367) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-23 14:09:57 -03:00
omo	4405513ca5	Option to select/target additional linear modules/layers in LORA training (#4178)	2023-10-22 15:57:19 -03:00
oobabooga	f17f7a6913	Increase the evaluation table height	2023-10-16 12:55:35 -07:00
oobabooga	188d20e9e5	Reduce the evaluation table height	2023-10-16 10:53:42 -07:00
oobabooga	71cac7a1b2	Increase the height of the evaluation table	2023-10-15 21:56:40 -07:00
oobabooga	fae8062d39	Bump to latest gradio (3.47) (#4258)	2023-10-10 22:20:49 -03:00
oobabooga	abe99cddeb	Extend evaluation slider bounds	2023-09-29 13:06:26 -07:00
oobabooga	1ca54faaf0	Improve --multi-user mode	2023-09-26 06:42:33 -07:00
John Smith	cc7b7ba153	fix lora training with alpaca_lora_4bit (#3853)	2023-09-11 01:22:20 -03:00
oobabooga	8545052c9d	Add the option to use samplers in the logit viewer	2023-08-22 20:18:16 -07:00
oobabooga	25e5eaa6a6	Remove outdated training warning	2023-08-22 13:16:44 -07:00
oobabooga	335c49cc7e	Bump peft and transformers	2023-08-22 13:14:59 -07:00
oobabooga	b96fd22a81	Refactor the training tab (#3619)	2023-08-18 16:58:38 -03:00
oobabooga	65aa11890f	Refactor everything (#3481)	2023-08-06 21:49:27 -03:00
oobabooga	3e70bce576	Properly format exceptions in the UI	2023-08-03 06:57:21 -07:00
Foxtr0t1337	85b3a26e25	Ignore values which are not string in training.py (#3287)	2023-07-25 19:00:25 -03:00
FartyPants	9b55d3a9f9	More robust and error prone training (#3058)	2023-07-12 15:29:43 -03:00
oobabooga	30f37530d5	Add back .replace('\r', '')	2023-07-12 09:52:20 -07:00
Fernando Tarin Morales	987d0fe023	Fix: Fixed the tokenization process of a raw dataset and improved its efficiency (#3035)	2023-07-12 12:05:37 -03:00
kabachuha	3f19e94c93	Add Tensorboard/Weights and biases integration for training (#2624)	2023-07-12 11:53:31 -03:00
kizinfo	5d513eea22	Add ability to load all text files from a subdirectory for training (#1997) ... * Update utils.py returns individual txt files and subdirectories to getdatasets to allow for training from a directory of text files * Update training.py minor tweak to training on raw datasets to detect if a directory is selected, and if so, to load in all the txt files in that directory for training * Update put-trainer-datasets-here.txt document * Minor change * Use pathlib, sort by natural keys * Space --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-07-12 11:44:30 -03:00
practicaldreamer	73a0def4af	Add Feature to Log Sample of Training Dataset for Inspection (#1711)	2023-07-12 11:26:45 -03:00
oobabooga	a17b78d334	Disable wandb during training	2023-07-12 07:19:12 -07:00
oobabooga	e3810dff40	Style changes	2023-07-11 18:49:06 -07:00
FartyPants	1f8cae14f9	Update training.py - correct use of lora_names (#2988)	2023-07-03 17:41:18 -03:00
FartyPants	48b11f9c5b	Training: added trainable parameters info (#2944)	2023-07-03 17:38:36 -03:00
FartyPants	ab1998146b	Training update - backup the existing adapter before training on top of it (#2902)	2023-06-27 18:24:04 -03:00
FartyPants	21c189112c	Several Training Enhancements (#2868)	2023-06-25 15:34:46 -03:00
oobabooga	95212edf1f	Update training.py	2023-06-25 12:13:15 -03:00
oobabooga	f0fcd1f697	Sort some imports	2023-06-25 01:44:36 -03:00
MikoAL	c40932eb39	Added Falcon LoRA training support (#2684) ... I am 50% sure this will work	2023-06-20 01:03:44 -03:00
FartyPants	ce86f726e9	Added saving of training logs to training_log.json (#2769)	2023-06-20 00:47:36 -03:00
Forkoz	9ab90d8b60	Fix warning for qlora (#2438)	2023-05-30 11:09:18 -03:00
oobabooga	3a6e194bc7	Change a warning message	2023-05-29 22:39:23 -03:00
oobabooga	acfd876f29	Some qol changes to "Perplexity evaluation"	2023-05-25 15:06:22 -03:00
oobabooga	63ce5f9c28	Add back a missing bos token	2023-05-24 13:54:36 -03:00
Alex "mcmonkey" Goodwin	3cd7c5bdd0	LoRA Trainer: train_only_after option to control which part of your input to train on (#2315)	2023-05-24 12:43:22 -03:00
oobabooga	e116d31180	Prevent unwanted log messages from modules	2023-05-21 22:42:34 -03:00