Commits · Dovakiins/qwerrwe

ORPO Trainer replacement (#1551)

7d1d22f
unverified

winglian commited on Apr 19

fix pretraining_ on odd datasets (#1463)

586bd8d
unverified

monsoon-nlp commited on Apr 2

fixes for dpo and orpo template loading (#1424)

7803f09
unverified

winglian commited on Mar 20

Feat: Add sharegpt multirole (#1137)

40a88e8
unverified

Nanobit commited on Mar 19

ORPO (#1419)

2ea70eb
unverified

winglian commited on Mar 18

add handling for argilla dpo-mix (#1397)

8a82d2e
unverified

winglian commited on Mar 12

Add Glaive conversation format support (#1365)

b7d8a7d
unverified

Brian Fitzgerald

winglian commited on Mar 11

allow the sharegpt handler to also better handle datasets destined for openai finetuning (#1361)

2598c9f
unverified

winglian commited on Mar 5

plain input/output prompt strategy w/o chat templates (#1346)

4d09b42
unverified

winglian commited on Mar 4

add gemma instruct chat template (#1341)

c1a7b3d
unverified

winglian commited on Feb 27

Support user-defined prompt processing strategies for dpo (#1248)

1e3d530
unverified

nopperl

winglian commited on Feb 26

Pretrain transforms (#1261)

c7cf381
unverified

winglian commited on Feb 6

relora: magnitude pruning of the optimizer (#1245)

8c2e05a
unverified

winglian commited on Feb 6

precompute dpo logprobs setting and fixes (#1199) [skip ci]

33e1170
unverified

winglian commited on Jan 25

Feat/chatml add system message (#1117)

98b4762
unverified

mhenrichsen Mads Henrichsen

winglian commited on Jan 25

DPO cleanup (#1126)

7523d1f
unverified

winglian

plaguss HF staff commited on Jan 23

add ultrachat prompt strategies (#996)

ba043a3
unverified

winglian commited on Dec 29, 2023

Respect sequence_len in config for `type: llama2_chat` (#926)

f1de29d
unverified

hamel commited on Dec 12, 2023

fixing prompt template of chatml by removal of linebreak (#922)

03c6318
unverified

timlim123 Timothy Lim commited on Dec 9, 2023

Update to adapt to sharegpt datasets with "assistant" rather than "gp… (#774)

0800885
unverified

MilesQLi

winglian commited on Oct 28, 2023

fixes for alpaca w chatml, and don't include attention_mask w mistral for flash attention (#728)

3553172
unverified

winglian commited on Oct 14, 2023

add support for defined train split (#654)

409ca0f
unverified

winglian commited on Sep 29, 2023

use fastchat conversations template (#578)

e7d3e2d
unverified

winglian commited on Sep 27, 2023

split completion text to sequence_len (#616)

97d3776
unverified

winglian commited on Sep 22, 2023

support custom field for completion from yml (#580)

f7a2263
unverified

winglian commited on Sep 15, 2023

feat: add Metharme prompt strategy (#446)

f474650
unverified

TearGosling

Nanobit commited on Aug 22, 2023

support user defined prompters, pretokenized datasets in config, local parquet, local arrow files (#348)

d2e7f27
unverified

winglian commited on Aug 20, 2023

fix orca prompts (#422)

1b7e860
unverified

winglian commited on Aug 16, 2023

Attention mask and position id fixes for packing (#285)

2bb0b78
unverified

winglian commited on Aug 12, 2023

Fix(message): Improve error message for bad format (#365)

e37d935
unverified

Nanobit commited on Aug 12, 2023

experimental llama 2 chat support (#296)

3392270
unverified

Jan Philipp Harries Jan Philipp Harries commited on Aug 6, 2023

Added Orca Mini prompt strategy (#263)

c93655c
unverified

Jan Philipp Harries Jan Philipp Harries commited on Aug 5, 2023

update prompts for open orca to match the paper (#317)

3d4984b
unverified

winglian commited on Jul 22, 2023

Fixed pre-commit problems, fixed small bug in logging_config to handle LOG_LEVEL env var

b1f4f7a

theobjectivedad commited on Jul 15, 2023

Adding logging enhancement

553a86b

theobjectivedad commited on Jul 14, 2023

Merge pull request #255 from OpenAccess-AI-Collective/open-orca-prompts

1e5014a
unverified

winglian commited on Jul 1, 2023

open orca support

78a1e1f

winglian commited on Jul 1, 2023

add option for instruct w sys prompts

924bbfd

winglian commited on Jun 29, 2023

Merge pull request #224 from OpenAccess-AI-Collective/system-prompt-data

f150c02
unverified

winglian commited on Jun 27, 2023

push intermediate model checkpoints to hub

612aabd

winglian commited on Jun 27, 2023

skip the system prompt

05ab909

winglian commited on Jun 26, 2023

pylint for duplicated code for system prompts

7b57ed7

winglian commited on Jun 18, 2023

add tests and supoort for loader for sys prompt data

3a38271

winglian commited on Jun 18, 2023

initial wip to get sys prompt from dataset

8d20e0a

winglian commited on Jun 17, 2023

bugfix for potential off by one

7925ddc

winglian commited on Jun 15, 2023

update alpaca_chat prompts for instructions to explainn the conversation

4b43a66

winglian commited on Jun 12, 2023

add new sharegpt, refactor prompt so it can be customized later, add exception if no data is processed

aac4b76

winglian commited on Jun 11, 2023

fix camel ai, add guanaco/oasst mapping for sharegpt

59bb219

winglian commited on Jun 7, 2023

new prompters, misc fixes for output dir missing using fsdp, and changing max seq len

4ac9e25

winglian commited on Jun 6, 2023

Update src/axolotl/prompt_strategies/alpaca_instruct.py

c17dae6

Nanobit

winglian commited on May 29, 2023

Commit History

ORPO Trainer replacement (#1551) 7d1d22f unverified

fix pretraining_ on odd datasets (#1463) 586bd8d unverified

fixes for dpo and orpo template loading (#1424) 7803f09 unverified

Feat: Add sharegpt multirole (#1137) 40a88e8 unverified

ORPO (#1419) 2ea70eb unverified

add handling for argilla dpo-mix (#1397) 8a82d2e unverified

Add Glaive conversation format support (#1365) b7d8a7d unverified

allow the sharegpt handler to also better handle datasets destined for openai finetuning (#1361) 2598c9f unverified

plain input/output prompt strategy w/o chat templates (#1346) 4d09b42 unverified

add gemma instruct chat template (#1341) c1a7b3d unverified

Support user-defined prompt processing strategies for dpo (#1248) 1e3d530 unverified

Pretrain transforms (#1261) c7cf381 unverified

relora: magnitude pruning of the optimizer (#1245) 8c2e05a unverified

precompute dpo logprobs setting and fixes (#1199) [skip ci] 33e1170 unverified

Feat/chatml add system message (#1117) 98b4762 unverified

DPO cleanup (#1126) 7523d1f unverified

add ultrachat prompt strategies (#996) ba043a3 unverified

Respect sequence_len in config for `type: llama2_chat` (#926) f1de29d unverified

fixing prompt template of chatml by removal of linebreak (#922) 03c6318 unverified

Update to adapt to sharegpt datasets with "assistant" rather than "gp… (#774) 0800885 unverified

fixes for alpaca w chatml, and don't include attention_mask w mistral for flash attention (#728) 3553172 unverified

add support for defined train split (#654) 409ca0f unverified

use fastchat conversations template (#578) e7d3e2d unverified

split completion text to sequence_len (#616) 97d3776 unverified

support custom field for completion from yml (#580) f7a2263 unverified

feat: add Metharme prompt strategy (#446) f474650 unverified

support user defined prompters, pretokenized datasets in config, local parquet, local arrow files (#348) d2e7f27 unverified

fix orca prompts (#422) 1b7e860 unverified

Attention mask and position id fixes for packing (#285) 2bb0b78 unverified

Fix(message): Improve error message for bad format (#365) e37d935 unverified

experimental llama 2 chat support (#296) 3392270 unverified

Added Orca Mini prompt strategy (#263) c93655c unverified

update prompts for open orca to match the paper (#317) 3d4984b unverified

Fixed pre-commit problems, fixed small bug in logging_config to handle LOG_LEVEL env var b1f4f7a

Adding logging enhancement 553a86b

Merge pull request #255 from OpenAccess-AI-Collective/open-orca-prompts 1e5014a unverified

open orca support 78a1e1f

add option for instruct w sys prompts 924bbfd

Merge pull request #224 from OpenAccess-AI-Collective/system-prompt-data f150c02 unverified

push intermediate model checkpoints to hub 612aabd

skip the system prompt 05ab909

pylint for duplicated code for system prompts 7b57ed7

add tests and supoort for loader for sys prompt data 3a38271

initial wip to get sys prompt from dataset 8d20e0a

bugfix for potential off by one 7925ddc

update alpaca_chat prompts for instructions to explainn the conversation 4b43a66

add new sharegpt, refactor prompt so it can be customized later, add exception if no data is processed aac4b76

fix camel ai, add guanaco/oasst mapping for sharegpt 59bb219

new prompters, misc fixes for output dir missing using fsdp, and changing max seq len 4ac9e25

Update src/axolotl/prompt_strategies/alpaca_instruct.py c17dae6