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
3,960 Commits 1 Branch 5 Tags
35d344b9518b3c51efbb447784e626c280b55a9e
Commit Graph

3960 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Llama
35d344b951 Remove torch dependency and more generic dim0 workaround 
Remove torch dependency from hf.py
Make workaround for dimension zero values of token_ids
more generic to handle every token, not just newlines.
 2023-05-03 09:48:16 -07:00
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
Llama
507da6fcf7 Merge pull request #30 from henk717/united 
Merge large refactor from united.
 2023-05-02 21:25:47 -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
somebody
a0f4ab5c6a Move bad token grabber until after newlinemode has been deduced 2023-05-02 20:23:36 -05:00
somebody
efe268df60 Move overrides to better places 2023-05-02 20:18:33 -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
Henk
de7b760048 Typo Fix 2023-05-03 01:02:50 +02:00
henk717
50c9ed3af1 Merge pull request #299 from one-some/model-structure-and-maybe-rwkv 
Structure changes
 2023-05-02 18:07:09 +02:00
somebody
111028642e Fix tokenizer fallback for llama 2023-05-01 19:42:52 -05:00
somebody
f6b5548131 Support safetensors in get_sharded_checkpoint_num_tensors 2023-05-01 19:15:27 -05:00
somebody
97e84928ba Download all shards correctly on aria2 and raise on bad load key 2023-05-01 18:53:36 -05:00
somebody
933dbd634a HFInferenceModel: Make badwordsids not unique to torch 2023-05-01 17:13:33 -05:00
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
somebody
ce3d465972 Remove some debug 2023-05-01 17:03:34 -05:00
Llama
eb4e89c2fa Merge pull request #29 from henk717/united 
Merge united
 2023-04-30 14:20:12 -07:00
Henk
545f79086d Ban EOS token in N mode 2023-04-30 18:48:22 +02:00
henk717
61511a5714 Merge pull request #341 from TinkerTankAI/united 
Update KoboldAI-Horde-Bridge to the latest version
 2023-04-29 15:09:15 +02:00
Tijs Zwinkels
2ad66ebcc0 Update KoboldAI-Horde-Bridge to the latest version 
This version contains a timeout on http requests,
preventing a hang in my worker.
 2023-04-29 15:07:32 +02:00
henk717
b19bd9c89e Merge branch 'KoboldAI:main' into united 2023-04-29 02:45:45 +02:00
Henk
1499763472 Flask fix 2023-04-29 02:44:41 +02:00
somebody
bfef79d2b8 Dynamic Fix 2023-04-28 18:55:38 -05:00
henk717
32ca5a716b Merge branch 'KoboldAI:main' into united 2023-04-28 22:29:22 +02:00
one-some
455b8257a9 Implement softprompt hack 2023-04-28 10:26:59 -05:00
one-some
fa6bb4b956 Potential fix for tpu dynamic 2023-04-28 10:17:48 -05:00
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
somebody
ace4364339 Two more time 2023-04-27 21:13:26 -05:00
somebody
446f38ee9d One more time 2023-04-27 21:07:34 -05:00
somebody
2eee535540 Actually fix decoding with soft prompts 
it really wants a tensor
 2023-04-27 21:01:12 -05:00
somebody
ffa7b22734 Experiment 2023-04-27 20:28:04 -05:00
somebody
cd1eb97c2a Debuuuug 2023-04-27 20:12:29 -05:00
somebody
4559112551 Potential fix 2023-04-27 19:51:10 -05:00
somebody
b256a8fbc7 Debug 2023-04-27 19:33:03 -05:00
henk717
e9e09c4b45 Merge pull request #338 from one-some/united 
Fix phantom 8 bit variable
 2023-04-28 02:09:07 +02:00
somebody
720b2ec7f0 Fix phantom variable 2023-04-27 19:05:38 -05:00
one-some
f9d162c001 Cut out things until it works 2023-04-27 10:10:17 -05:00
henk717
945aec2320 Merge pull request #288 from vanderh0ff/dev 
updated micro mamba user directory to match username
 2023-04-27 16:12:29 +02:00
henk717
b0bbdc0c29 Merge pull request #333 from ebolam/united 
New Editor
 2023-04-27 15:52:13 +02:00
ebolam
890aa277f1 Now refreshes the browser when reconnecting to socketio 2023-04-27 08:43:07 -04:00
ebolam
8b64f006e8 Set the browser to refresh when loading a story to fix a race condition 2023-04-27 08:17:55 -04:00
ebolam
a9ac3319cf Bug Fix 2023-04-27 08:00:30 -04:00
ebolam
4bd193afe0 Second welcome bug fix 2023-04-26 20:16:28 -04:00
ebolam
7d986effa1 Fix for welcome area showing on loading a story when it shouldn't 2023-04-26 20:01:17 -04:00
ebolam
782e9e5fa0 Another fix 2023-04-26 19:55:15 -04:00
onesome
467f2f25eb More loading fixes 2023-04-26 16:58:33 -05:00
onesome
d4f7b60dc9 Fix for multiple paths 2023-04-26 16:49:12 -05:00