marijnfs 3367fca732 Gradio configuration parameters (#1591) ...

* Gradio Configuration Settings

* Making various Gradio variables configurable instead of hardcoded

* Remove overwriting behavour of 'default tokens' that breaks tokenizer for llama3

* Fix type of gradio_temperature

* revert un-necessary change and lint

---------

Co-authored-by: Marijn Stollenga <stollenga@imfusion.de>
Co-authored-by: Marijn Stollenga <stollenga@imfusion.com>
Co-authored-by: Wing Lian <wing.lian@gmail.com>

2024-05-06 15:43:42 -04:00

..

cli

Gradio configuration parameters (#1591)

2024-05-06 15:43:42 -04:00

common

support for true batches with multipack (#1230)

2024-02-01 10:18:42 -05:00

core

improve save callbacks (#1592)

2024-05-04 23:19:18 -04:00

models

Phi2 multipack (#1173)

2024-01-23 12:54:36 -05:00

monkeypatch

Add support for Gemma chat template (#1530)

2024-04-21 19:55:40 -04:00

prompt_strategies

ORPO Trainer replacement (#1551)

2024-04-19 17:25:36 -04:00

utils

Gradio configuration parameters (#1591)

2024-05-06 15:43:42 -04:00

__init__.py

WIP for axolotl trainer

2023-04-14 00:20:05 -04:00

convert.py

Lint convert.py

2023-05-31 02:53:53 +09:00

datasets.py

Pretrain transforms (#1261)

2024-02-06 00:37:03 -05:00

logging_config.py

Don't disable existing loggers when configuring axolotl logging (#1395)

2024-03-14 11:05:21 -04:00

loraplus.py

lora+ support (#1352)

2024-03-05 07:29:23 -05:00

prompt_tokenizers.py

Feat: Add sharegpt multirole (#1137)

2024-03-19 20:51:49 +09:00

prompters.py

Feat: Add sharegpt multirole (#1137)

2024-03-19 20:51:49 +09:00

train.py

Pass weakref to model in the SIGINT handler to free up model post train function (#1581)

2024-05-03 11:05:28 -04:00