 Artidoro Pagnoni
|
5111741384
|
freezing embeddings and known issue
|
2023-07-18 04:22:33 -07:00 |
|
|
Artidoro Pagnoni
|
845188de11
|
Update README.md
|
2023-07-17 09:00:28 -07:00 |
|
|
artidoro
|
cc488110b5
|
human ratings
|
2023-06-08 13:20:51 -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
|
4ea02e7464
|
Merge pull request #126 from tobi/rank-and-files
Rank and files
|
2023-06-06 11:43:50 -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 |
|
|
Artidoro Pagnoni
|
bdc655dfa7
|
Merge pull request #102 from steremma/steremma-patch-1
Respect cache_dir passed by user
|
2023-06-01 07:37:40 -07:00 |
|
|
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 |
|
|
Artidoro Pagnoni
|
86ac6016f6
|
Update the scripts with HF checkpoints
|
2023-05-31 22:44:30 -07:00 |
|
|
David Meikle
|
8ee760d80e
|
Added use_auth_token to model arguments to load private models
|
2023-06-01 06:14:32 +01:00 |
|
|
Artidoro Pagnoni
|
43643cab5d
|
Reordering README.md
|
2023-05-31 20:22:15 -07:00 |
|
|
Artidoro Pagnoni
|
e598fe8f8f
|
multi-gpu discussion
|
2023-05-31 20:20:00 -07:00 |
|
|
Artidoro Pagnoni
|
0b46ca80a0
|
add guanaco repro scripts
|
2023-05-31 20:17:51 -07:00 |
|
|
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
|
460525b4fe
|
gitignore
|
2023-05-31 18:12:47 -07:00 |
|
|
Artidoro Pagnoni
|
d69e26db70
|
requirements
|
2023-05-31 16:41:29 -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
|
9991dc555c
|
Update README.md
|
2023-05-30 13:34:46 -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 |
|
|
Artidoro Pagnoni
|
f96eec1675
|
Merge pull request #63 from pmysl/main
Suppress pad_token warning message
|
2023-05-28 13:46:32 -07:00 |
|
|
Piotr Myśliński
|
e31aedd4ba
|
Suppress pad_token warning message
|
2023-05-28 14:00:12 +02:00 |
|
|
Artidoro Pagnoni
|
ce5e5be9de
|
Merge pull request #58 from muelletm/patch-1
Set per_device_eval_batch_size in finetune.sh
|
2023-05-27 20:32:24 -07:00 |
|
|
Artidoro Pagnoni
|
204dda82c4
|
Merge pull request #51 from pmysl/main
Fix link to inference notebook
|
2023-05-27 20:29:42 -07:00 |
|
|
Artidoro Pagnoni
|
af55cf0c62
|
Merge pull request #20 from Qubitium/check-llama
Check for LlamaTokenizerFast rather than infer type from path name.
|
2023-05-27 20:23:17 -07:00 |
|
|
Artidoro Pagnoni
|
a3809620ee
|
Adding guanaco openassistant dataset
|
2023-05-27 17:01:08 -07:00 |
|
|
Thomas Müller
|
3926ee5c02
|
Update finetune.sh
Fixes a copy paste error where per_device_train_batch_size was set twice.
|
2023-05-27 20:33:23 +02:00 |
|
|
Piotr Myśliński
|
530382b430
|
Fix link to inference notebook
|
2023-05-27 10:32:46 +02:00 |
|
|
KKCorps
|
f1d1b2901a
|
Remove resetting old state to fix empty adapters
|
2023-05-26 22:02:16 +05:30 |
|
|
Artidoro Pagnoni
|
073a4856f9
|
Update README.md
|
2023-05-25 12:13:57 -07:00 |
|
|
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
|
e3817441cc
|
fast demo
|
2023-05-24 08:36:26 -07:00 |
|
|
Artidoro Pagnoni
|
a472fa1af0
|
demo info
|
2023-05-24 08:04:05 -07:00 |
|
|
Artidoro Pagnoni
|
3ba09cba37
|
Update README.md
|
2023-05-24 07:37:50 -07:00 |
|
|
Artidoro Pagnoni
|
55c643ed69
|
added demo links
|
2023-05-24 07:24:35 -07:00 |
|
|
Artidoro Pagnoni
|
cc962c9e61
|
demo notebook
|
2023-05-24 07:00:10 -07:00 |
|
|
Artidoro Pagnoni
|
a757cb1164
|
gradio colab demo
|
2023-05-24 06:43:55 -07:00 |
|
|
Artidoro Pagnoni
|
bbbfc81ef0
|
installation info
|
2023-05-24 05:14:49 -07:00 |
|
|
Artidoro Pagnoni
|
3c0358774b
|
distinguish gpt vs guanaco
|
2023-05-24 04:56:34 -07:00 |
|
|
Artidoro Pagnoni
|
dd9a2c4651
|
Update README.md
|
2023-05-24 01:24:30 -07:00 |
|
|
Artidoro Pagnoni
|
088f9265ea
|
adding qualitative example notebook
|
2023-05-24 01:17:46 -07:00 |
|
|
Artidoro Pagnoni
|
6f91610405
|
adding qualitative example notebook
|
2023-05-24 01:15:52 -07:00 |
|