Zach
|
311c818934
|
feat: evals on new gptj models
|
2023-04-10 02:14:20 +00:00 |
|
Adam Treat
|
47d3fd1621
|
Comment out the list of chat features until it is ready.
|
2023-04-09 20:23:52 -04:00 |
|
Adam Treat
|
b8f8a37d87
|
Working efficient chat context.
|
2023-04-09 14:03:53 -04:00 |
|
Adam Treat
|
6ce4089c4f
|
Prelim support for past context.
|
2023-04-09 13:01:29 -04:00 |
|
Adam Treat
|
91a2602d93
|
Naive version of chat context, but slow.
|
2023-04-09 13:01:29 -04:00 |
|
Zach
|
195f8a7d4e
|
fix: topic model for embeddings
|
2023-04-09 15:12:49 +00:00 |
|
Adam Treat
|
596592ce12
|
Time how long it takes to process the prompt.
|
2023-04-09 10:24:47 -04:00 |
|
Adam Treat
|
df86980002
|
Fix padding.
|
2023-04-09 07:38:41 -04:00 |
|
adtreat
|
6b55a48068
|
Update README.md
|
2023-04-09 01:37:12 -04:00 |
|
adtreat
|
35895a5819
|
Update README.md
|
2023-04-09 01:36:31 -04:00 |
|
adtreat
|
9ea40305dc
|
Update README.md
|
2023-04-09 01:35:19 -04:00 |
|
Adam Treat
|
bd5e279621
|
Don't display the endoftext token.
|
2023-04-09 01:22:12 -04:00 |
|
Adam Treat
|
02e13737f3
|
Don't repeat the prompt in the response.
|
2023-04-09 01:11:52 -04:00 |
|
Adam Treat
|
0903da3afa
|
Update README.md
|
2023-04-09 00:03:15 -04:00 |
|
Adam Treat
|
ed68a2cccb
|
Update README.md
|
2023-04-09 00:01:42 -04:00 |
|
Adam Treat
|
dfe9d43c5e
|
Update README.md
|
2023-04-08 23:54:25 -04:00 |
|
Adam Treat
|
04f7dbb395
|
Update README.md
|
2023-04-08 23:53:24 -04:00 |
|
Adam Treat
|
243972e3d8
|
Update README.md
|
2023-04-08 23:46:23 -04:00 |
|
adtreat
|
65837727a7
|
Update README.md
|
2023-04-08 23:41:49 -04:00 |
|
Adam Treat
|
ff2fdecce1
|
Initial commit.
|
2023-04-08 23:28:39 -04:00 |
|
Zach Nussbaum
|
7807a80bbb
|
fix: bs try one more time?
|
2023-04-08 21:47:07 +00:00 |
|
Zach Nussbaum
|
2f0eba211d
|
fix: smaller bs for 40gb
|
2023-04-08 21:36:20 +00:00 |
|
Zach Nussbaum
|
7f95ab3a06
|
fix: config for lora gptj
|
2023-04-08 21:17:12 +00:00 |
|
Zach Nussbaum
|
9efdf56e38
|
fix: saving name
|
2023-04-08 20:56:13 +00:00 |
|
Zach Nussbaum
|
633df8edb4
|
Merge remote-tracking branch 'origin/mosaic' into gptj
|
2023-04-08 20:47:01 +00:00 |
|
Zach Nussbaum
|
31195270cb
|
fix: eos/pad token + wd
|
2023-04-08 20:38:10 +00:00 |
|
Zach Nussbaum
|
c82ee7d882
|
fix: add wd + min lr to config
|
2023-04-08 20:37:51 +00:00 |
|
Zach Nussbaum
|
be3f528810
|
fix: tokenization error
|
2023-04-08 20:33:51 +00:00 |
|
Zach Nussbaum
|
b66f127ade
|
fix: config + ignore pkl
|
2023-04-08 20:33:02 +00:00 |
|
Zach Nussbaum
|
0606ab46b9
|
feat: build map script
|
2023-04-08 19:30:53 +00:00 |
|
Zach
|
1c6d2d9622
|
fix: embeddings instead of logits!!!
|
2023-04-08 17:05:40 +00:00 |
|
zanussbaum
|
147c2fd7eb
|
feat: lora gptj
|
2023-04-07 17:53:07 -04:00 |
|
zanussbaum
|
2b001e8932
|
fix: batch size
|
2023-04-07 17:41:45 -04:00 |
|
zanussbaum
|
7cfda6a21f
|
feat: update for mosaic
|
2023-04-07 16:54:29 -04:00 |
|
Zach Nussbaum
|
4b51e6ef37
|
fix: pyarrow filter
|
2023-04-07 19:04:19 +00:00 |
|
Andriy Mulyar
|
ed53fe1966
|
Updated roadmap and links.
|
2023-04-07 13:53:47 -04:00 |
|
Zach Nussbaum
|
7a9f6d1cdc
|
fix: inference save shards
|
2023-04-07 16:23:34 +00:00 |
|
Andriy Mulyar
|
8e28a33731
|
Merge pull request #268 from MalikMAlna/dev
Slight cleanup
|
2023-04-07 10:50:56 -04:00 |
|
Andriy Mulyar
|
7d06b4cd23
|
Merge pull request #267 from dte/patch-1
Update README.md
|
2023-04-07 10:50:27 -04:00 |
|
Andriy Mulyar
|
c5d010f352
|
Correct MD5 Hash
|
2023-04-07 10:50:02 -04:00 |
|
Andriy Mulyar
|
d8cde6d272
|
Update README.md
|
2023-04-07 10:47:15 -04:00 |
|
Zach
|
0bd6acb4dd
|
fix: drop uneven batch size
|
2023-04-07 12:09:31 +00:00 |
|
Zach
|
985da51fbc
|
fix: concat
|
2023-04-07 04:33:34 +00:00 |
|
Zach
|
1b14b1f723
|
fix: data for inference
|
2023-04-07 01:45:07 +00:00 |
|
Zach
|
fb9ff9c40d
|
feat: inference for embedding plots
|
2023-04-07 01:40:39 +00:00 |
|
MalikMAlna
|
43ddc3eefa
|
Rephrasing comment for clarity
|
2023-04-06 20:20:18 -04:00 |
|
MalikMAlna
|
0689c2e974
|
Changing single to double quotes for quote consistency
|
2023-04-06 20:07:08 -04:00 |
|
MalikMAlna
|
604176ace8
|
Slight cleanup of superfluous comment and space after commas
|
2023-04-06 19:57:46 -04:00 |
|
MalikMAlna
|
b3be94a0ef
|
Slight cleanup of superfluous comment and space after comma
|
2023-04-06 19:56:49 -04:00 |
|
Dillon Erb
|
416eaf1d28
|
Update README.md
|
2023-04-06 18:11:05 -04:00 |
|