qwerrwe / src /axolotl /prompt_strategies

Commit History

add ultrachat prompt strategies (#996)
ba043a3
unverified

winglian commited on

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

hamel commited on

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

timlim123 Timothy Lim commited on

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

MilesQLi winglian commited on

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

winglian commited on

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

winglian commited on

use fastchat conversations template (#578)
e7d3e2d
unverified

winglian commited on

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

winglian commited on

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

winglian commited on

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

TearGosling Nanobit commited on

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

winglian commited on

fix orca prompts (#422)
1b7e860
unverified

winglian commited on

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

winglian commited on

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

Nanobit commited on

experimental llama 2 chat support (#296)
3392270
unverified

Jan Philipp Harries Jan Philipp Harries commited on

Added Orca Mini prompt strategy (#263)
c93655c
unverified

Jan Philipp Harries Jan Philipp Harries commited on

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

winglian commited on

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

theobjectivedad commited on

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

winglian commited on

open orca support
78a1e1f

winglian commited on

add option for instruct w sys prompts
924bbfd

winglian commited on

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

winglian commited on

push intermediate model checkpoints to hub
612aabd

winglian commited on

skip the system prompt
05ab909

winglian commited on

pylint for duplicated code for system prompts
7b57ed7

winglian commited on

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

winglian commited on

initial wip to get sys prompt from dataset
8d20e0a

winglian commited on

bugfix for potential off by one
7925ddc

winglian commited on

update alpaca_chat prompts for instructions to explainn the conversation
4b43a66

winglian commited on

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

winglian commited on

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

winglian commited on

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

winglian commited on

Update src/axolotl/prompt_strategies/alpaca_instruct.py
c17dae6

Nanobit winglian commited on

Apply isort then black
37293dc

Nanobit commited on

Fix mypy typing
e9650d3

Nanobit commited on

Refactor duplicate code between Prompter and Pygmalion
8e46c0f

Nanobit commited on

Lint pygmalion
01c8a33

Nanobit commited on

Lint creative_acr
1645a4d

Nanobit commited on

Lint alpaca_instruct
145b060

Nanobit commited on

Lint alpaca_chat
8cc0aad

Nanobit commited on

Fix lint
903ea30

Nanobit commited on

apply black formatting
ce34d64

winglian commited on

fix enum pass as value
fb100a9

winglian commited on

Add qa style data for alpaca instructions, fix one_cycle scheduler
3a50377

winglian commited on

fix new dataset prompt tokenizers
0f74464

winglian commited on

add missing __init__
e0602a9

winglian commited on

pygmalion dataset prompts format, cached tokenized datasets should be hashed on the tokenizer too
2809f3f

winglian commited on

tokenization fixes
4ea9a66

winglian commited on