 Artidoro Pagnoni
|
5111741384
|
freezing embeddings and known issue
|
2023-07-18 04:22:33 -07:00 |
|
|
Artidoro Pagnoni
|
3da535abdf
|
Merge pull request #101 from dameikle/main
Added use_auth_token to model arguments to load private models
|
2023-06-06 11:49:29 -07:00 |
|
|
Artidoro Pagnoni
|
f4ee7fd786
|
Update qlora.py
Co-authored-by: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com>
|
2023-06-06 11:31:24 -07:00 |
|
|
Tobias Lütke
|
00e5ad2a75
|
pandas is better at reading lines
|
2023-06-03 19:46:39 -04:00 |
|
|
Tobias Lütke
|
bed4b0d863
|
typo
|
2023-06-03 19:42:49 -04:00 |
|
|
Tobias Lütke
|
e69303d556
|
introduce LOCAL_RANK mapping and optiojn to leave input data as-is
|
2023-06-03 19:30:39 -04:00 |
|
|
Stergiadis Manos
|
986c500c5b
|
Respect cache_dir passed by user
When the user overrides default `cache_dir` we should respect it not only for tokenizer but also for the model
|
2023-06-01 13:40:55 +02:00 |
|
|
David Meikle
|
8ee760d80e
|
Added use_auth_token to model arguments to load private models
|
2023-06-01 06:14:32 +01:00 |
|
|
Artidoro Pagnoni
|
a45718eec2
|
fix tokenization issues
|
2023-05-31 19:52:43 -07:00 |
|
|
Artidoro Pagnoni
|
5f618e7e90
|
oasst1 and bug fixes
|
2023-05-31 18:16:00 -07:00 |
|
|
Artidoro Pagnoni
|
94e50419e3
|
Merge pull request #86 from dred0n/feature-local-training-data
add support local training data
|
2023-05-31 14:27:33 -07:00 |
|
|
Artidoro Pagnoni
|
d9f201c2b6
|
Merge pull request #79 from KKcorps/resume_patch
Bug Fix: Resume training from checkpoints
|
2023-05-31 14:22:00 -07:00 |
|
|
Artidoro Pagnoni
|
7e1e81445b
|
Merge pull request #44 from KKcorps/empty_adapter_patch
Bug Fix: 443 Bytes `adapter_model.bin` files
|
2023-05-30 11:56:00 -07:00 |
|
|
Dredon
|
ace51b6e34
|
add jsonl local dataset support
|
2023-05-30 10:45:11 -05:00 |
|
|
Dredon
|
2e21c16297
|
add csv, tsv support
|
2023-05-30 09:43:49 -05:00 |
|
|
Dredon
|
c06d702e5f
|
add support local training set support
|
2023-05-30 08:52:20 -05:00 |
|
|
KKCorps
|
163adf26a6
|
Only load adapter weights on resume
|
2023-05-29 14:57:21 +05:30 |
|
|
Piotr Myśliński
|
e31aedd4ba
|
Suppress pad_token warning message
|
2023-05-28 14:00:12 +02:00 |
|
|
KKCorps
|
f1d1b2901a
|
Remove resetting old state to fix empty adapters
|
2023-05-26 22:02:16 +05:30 |
|
|
Qubitium
|
8532e0117d
|
Check for LlamaTokenizerFast rather than infer type from path name. Fix cases where non-standard llama model path names gets bypassed in tokenizer check. The tokenizer is init with use_fast=True and qlora requires >4.29.2 transformers so the only possible tokenizer is LlamaTokenizerFast.
|
2023-05-25 08:56:14 +00:00 |
|
|
Artidoro Pagnoni
|
9f684a4c8c
|
Merge pull request #2 from scottlogic-alex/support-mpt
support trusting remote code (to unpickle MPT-based models)
|
2023-05-22 11:19:44 -07:00 |
|
|
Alex Birch
|
7e4b88cbaf
|
remove broken logger.log() call (was not specifying which log level to use). put the message in the error instead.
|
2023-05-22 19:01:20 +01:00 |
|
|
Alex Birch
|
765455f2d6
|
support trusting remote code (to unpickle MPT-based models)
|
2023-05-22 18:34:31 +01:00 |
|
|
Artidoro Pagnoni
|
132e0510f0
|
rename and cleanup
|
2023-05-12 12:14:23 -07:00 |
|