Commit History
precompute dpo logprobs setting and fixes (#1199) [skip ci]
33e1170
unverified
Feat/chatml add system message (#1117)
98b4762
unverified
add colab example (#1196) [skip ci]
ee0b5f6
unverified
JohanWork
commited on
fix(log): improve warning to clarify that lora_modules_to_save expect a list (#1197)
08719b9
unverified
prepare for release 0.4.0 (#1175)
1427d5b
unverified
Mixtral fixes 20240124 (#1192) [skip ci]
54d2ac1
unverified
Standardize system prompt format for AlpacaPrompter (#1190) [skip ci]
af02430
unverified
Oleh Kuznetsov
commited on
upgrade deepspeed to 0.13.1 for mixtral fixes (#1189) [skip ci]
8a49309
unverified
more dpo fixes for dataset loading and docs (#1185) [skip ci]
5bce45f
unverified
report min lenght of tokenized data (#1186) [skip ci]
d85d494
unverified
Fix generation_config validation raises Exception for do_merge_lora (#1184)
02f2c72
unverified
Add support for offline mode with HF_HUB_OFFLINE envvar (#1182)
71141de
unverified
Update rlhf.md (#1178) [skip ci]
dc051b8
unverified
Aleksey Korshuk
commited on
DPO fixes v2 (#1174)
59a31fe
unverified
Phi2 multipack (#1173)
814aee6
unverified
update docs [skip ci] (#1176)
b715cd5
unverified
don't fail if can't cast weights due to offload when merging (#1172) [skip ci]
fb7f9b9
unverified
Fine-Tuning Mistral-7b for Real-World Chatbot Applications Using Axolotl (Lora used) (#1155)
cc25039
unverified
Update README.md (#1169) [skip ci]
9135b9e
unverified
Ayush Singh
commited on
Feat(test): Add tests for alpaca chatml prompt tokenizer (#1088)
5439707
unverified
Add desc to map/filter (#1162)
6840381
unverified
support for explicit test_dataset definition for evals (#786)
cda52dc
unverified
Falcon embeddings (#1149) [skip docker]
e799e08
unverified
add commit message option to skip docker image builds in ci (#1168) [skip ci]
0f77b8d
unverified
Vram fix attempt (#1164) [skip ci]
32580c1
unverified
improve vram use w gradient checkpointing (#1167) [skip ci]
802f966
unverified
Add mlflow callback for pushing config to mlflow artifacts (#1125)
b8e5603
unverified
JohanWork
commited on
jupyter lab fixes (#1139) [skip ci]
eaaeefc
unverified
Qwen2 (#1166)
f5a828a
unverified
make sure the model config loader respects the model_revision too (#1160) [skip-ci]
fccb542
unverified
Deprecate max packed sequence len (#1141)
2ce5c0d
unverified
feat(dataset): add config to keep processed dataset in memory (#1152)
3db5f2f
unverified
fix check for env var (#1151)
cbecf3e
unverified
Dockerfile cloud ports (#1148)
729740d
unverified
Fix link for Minotaur model (#1146) [skip-ci]
08b8ba0
unverified
Multipack simplify for Mixtral (#1142)
6910e6a
unverified
fix bf16 check when preprocessing data (#1140)
317fa25
unverified
fix(preprocess): Make sure dataset not loaded from cache when using preprocess cli (#1136)
1e56b88
unverified
Preprocess dataset size fix (#1131)
7570446
unverified
Agnostic cloud gpu docker image and Jupyter lab (#1097)
ece0211
unverified
Add `layers_to_transform` for `lora_config` (#1118)
8487b97
unverified
xzuyn
commited on
fix(readme): clarify custom user prompt [no-ci] (#1124)
9cd27b2
unverified
pin model_revision for phi2 (#1123)
c1b741d
unverified
update PR template so we can capture twitter or discord handles (#1121) [skip ci]
0abf4d6
unverified
Enable or disable bf16 support based on availability (#1116)
0865613
unverified
Simon Hällqvist
commited on