rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-06-05 21:59:24 +02:00
Code Issues Projects Releases Wiki Activity
3,974 Commits 1 Branch 5 Tags
2730879c61273a4484d66a5fcfc195d45d7af015
Commit Graph

1549 Commits

Author SHA1 Message Date
Henk
2730879c61 Better warning until something more robust is in 2023-05-05 21:28:06 +02:00
Henk
d508b4a319 More max_context_length flexibility 2023-05-05 19:50:56 +02:00
Henk
33969b5845 Basic HF code execution support 2023-05-05 17:23:01 +02:00
henk717
7f5242db17 Merge pull request #344 from pi6am/fix/llama-tokens 
Fix/llama tokens
 2023-05-03 19:07:47 +02:00
ebolam
fa3611b994 Update to United 
Update to United
 2023-05-03 10:54:17 -04:00
Llama
3768848548 Fix tokenization and whitespace issues with llama-derived models 
Work around the 'soft' prefix space behavior of sentencepiece.
Override encode to restore the deleted HF support for decode_with_prefix_space.
Override decode to skip the soft space and return true decoded tokens.
Allow submitting chat messages with embedded newlines.
Split sentences between punctuation and whitespace, rather than after whitespace.
Also include trailing quotes and brackets after sentence stoppers.
This avoids splitting ." and .) into two tokens, for instance.
Insert whitespace at the beginning of the author's note, since sentences are
split with leading whitespace.
Remove spurious newlines at the end of chat responses.
 2023-05-03 01:27:11 -07:00
Henk
5d1ee39250 Fix loadmodelsettings 2023-05-03 04:21:37 +02:00
henk717
724ba43dc1 Merge pull request #342 from one-some/model-structure-and-maybe-rwkv 
Move overrides to better places
 2023-05-03 03:34:17 +02:00
somebody
4b3b240bce Move loadmodelsettings 2023-05-02 20:33:37 -05:00
Henk
480919a2a7 Nicer way of serving lite 2023-05-03 01:16:02 +02:00
Henk
03e10bed82 /lite (Not functional yet) 2023-05-03 01:04:51 +02:00
somebody
c95be636a4 Merge branch 'united' of https://github.com/henk717/KoboldAI into model-structure-and-maybe-rwkv 2023-05-01 17:08:20 -05:00
ebolam
5a32159e58 Remove debug prints 2023-05-01 10:53:02 -04:00
Henk
545f79086d Ban EOS token in N mode 2023-04-30 18:48:22 +02:00
one-some
19817a271b More colab 2023-04-28 10:16:15 -05:00
one-some
b3614b64b1 Hello Colab 2023-04-28 10:10:26 -05:00
one-some
f9d162c001 Cut out things until it works 2023-04-27 10:10:17 -05:00
henk717
b0bbdc0c29 Merge pull request #333 from ebolam/united 
New Editor
 2023-04-27 15:52:13 +02:00
onesome
9579298df7 Better fallback 2023-04-25 22:28:07 -05:00
onesome
98cd6aa246 Make RWKV experimental 2023-04-25 17:13:06 -05:00
onesome
b8bef641ff Merge branch 'united' of https://github.com/henk717/KoboldAI into model-structure-and-maybe-rwkv 2023-04-25 16:54:53 -05:00
Henk
9eaa2aba47 Isolate OPT Tokenizer Fix to OPT models 2023-04-25 22:49:56 +02:00
ebolam
d7c46f668c fix tab vs space error 2023-04-21 14:11:51 -04:00
ebolam
3990e67b81 Merge commit 'refs/pull/378/head' of https://github.com/ebolam/KoboldAI into united 2023-04-21 08:27:36 -04:00
ebolam
a34ce85d21 Fix for UI1 remote mode file loading from browser 2023-04-16 20:43:03 -04:00
Henk
2926dac72b Don't print allowed_ips if unused 2023-04-16 23:59:13 +02:00
somebody
5dd67d027a Workaround for socketio context errors for loading 2023-04-15 18:54:21 -05:00
somebody
08b4e317ff Fix double slashing 2023-04-15 13:30:05 -05:00
somebody
d3a73aaeba Fix api 2023-04-15 13:17:20 -05:00
somebody
4dcf570407 Fix legacy model loading 2023-04-15 12:57:35 -05:00
Henk
b68860b3de Workaround to make --host work again 2023-04-15 18:31:39 +02:00
one-some
1b500c7179 Merge pull request #5 from LostRuins/concedo_api 
Added stop sequences functionality for API calls
 2023-04-15 10:51:31 -05:00
somebody
b2e6fcfe3a Remove line that sets disk_layers to None always 
whoops
 2023-04-15 10:41:10 -05:00
Henk
3eda7269f7 Fix incorrect host merge 2023-04-15 14:58:24 +02:00
Concedo
9705b7b79c increase API version (+1 squashed commits) 
Squashed commits:

[c168c08] Added stop sequences functionality for API calls
 2023-04-15 18:09:53 +08:00
somebody
ea8df4c0d3 Merge branch 'united' of https://github.com/henk717/KoboldAI into model-structure-and-maybe-rwkv 2023-04-14 20:38:56 -05:00
ebolam
be0319cf03 added VERSION link in the left flyout menu footer that will show which git REPO and BRANCH the system is running on. 
Fix for pasting text into the game area
Fix for ctrl+a then delete
Fix for changing text then back/forward a bunch loosing text
 2023-04-14 13:54:11 -04:00
Henk
bde9c6980f Transformers 4.28 support 2023-04-14 14:13:46 +02:00
somebody
3e8e3a18b0 Fix for custom gpt2 2023-04-09 18:23:52 -05:00
somebody
fedbffd07b Small fixes 
Typos galore!
 2023-04-09 13:35:28 -05:00
YellowRoseCx
71e5d23a5b Add IP whitelisting to --host 2023-04-05 21:23:24 -05:00
Henk
4a8b099888 Model loading fix 2023-04-02 00:29:56 +02:00
Henk
90a7eb6153 LLama tokenizer settings 2023-03-17 12:40:08 +01:00
somebody
b93c339145 Model: Lazyload backends 2023-03-13 20:29:29 -05:00
somebody
3adc67c7a4 RWKV: Move import right before usage 
So we don't needlessly compile the cuda kernel
 2023-03-13 19:37:45 -05:00
somebody
b10b201701 Model: Add basic RWKV implementation 2023-03-13 19:34:38 -05:00
somebody
60793eb121 Make modellist easier to work with 2023-03-13 15:40:24 -05:00
jojorne
c87ef60db1 revert more unrelated code 2023-03-11 13:48:41 -03:00
jojorne
423c022648 Fix save loading between v1 and v2 to v3 with wi features 2023-03-11 13:14:46 -03:00
somebody
38c4edac40 Model: Fix eos/bos padding issue 
Weird config None assignments
 2023-03-10 20:01:01 -06:00