ebolam
26aabaa6fb
Merge branch 'henk717:united' into UI2
2023-01-31 07:34:08 -05:00
Henk
6def9abebc
Model setting fixes
2023-01-31 03:06:07 +01:00
Henk
143d279f2a
Don't save revision
2023-01-31 02:03:29 +01:00
somebody
63121b2b89
Fix calc_ai_text when no actions are present
2023-01-22 14:54:26 -06:00
ebolam
a0249d7ffa
Changed image return to show last image rather than returning null if the action doesn't have an image
2023-01-19 12:35:55 -05:00
ebolam
4f17e541ee
Merge branch 'UI2' of https://github.com/ebolam/KoboldAI into UI2
2023-01-13 07:46:48 -05:00
ebolam
e7effced13
Fix leaking usegpu and hascuda to the system save which can cause issues on colab.
2023-01-13 07:46:38 -05:00
ebolam
bd72b05e12
Fix for editting an action with a matched world info
2023-01-10 20:15:26 -05:00
ebolam
9b1138bafa
Added in alternative rep pen calculation (log instead of linear application) as an option.
2023-01-10 08:45:55 -05:00
ebolam
33dc4aa749
Remove Debugging
2023-01-09 20:04:05 -05:00
ebolam
4668bc8ec0
Fix for bug that crashes generation when using soft prompts
2023-01-09 19:56:49 -05:00
henk717
535b9bdfdf
Merge pull request #251 from one-some/bias-improvements
...
Bias improvements
2023-01-08 17:45:41 +01:00
somebody
76c1398917
Small cleanup with imports
...
and unused threading code
2023-01-07 20:19:31 -06:00
Henk
2d85046493
Typo Fix
2023-01-07 21:35:58 +01:00
ebolam
bf7fb52d46
Fix for tortoiseTTS crashing TTS if not installed (should be optional)
2023-01-07 15:22:09 -05:00
henk717
b4c2fa0dc1
Merge pull request #245 from pi6am/feat/flexible-memory-length
...
Change the maximum memory length to be based on the token budget
2023-01-06 16:30:58 +01:00
Llama
b28cc01dba
Change the maximum memory length to be based on the token budget
...
The maximum memory length was hardcoded to 512 tokens independent of
the overall context token budget. This was restrictive when the token
budget was increased, and excessive when the budget was decreased.
Based on feedback, this change modifies the max memory length to be 50%
of the context length. I tested with a memory consisting of the first
five paragraphs of The Three Musketeers, and the change seemed
reasonable with context lengths of 512, 1024 and 2048.
In order to minimize changes, this commit only modifies
max_memory_length; max_prompt_length and max_authornote_length are still
hardcoded as 512 tokens. We might want to make the max prompt length
flexible in the future, but since the author's note is injected into
the story, it's probably fine to restrict its length since a long
author's note will likely derail the AI.
2023-01-06 00:36:32 -08:00
somebody
8460b0de68
Removed option to disable model attribution
...
Some models have robot attribution as a requirement in the usage
agreement
2023-01-04 17:22:47 -06:00
somebody
ab0277549c
Merge branch 'united' of https://github.com/henk717/KoboldAI into screenshot
2023-01-02 12:14:38 -06:00
Llama
48dd451a8c
Add the ability to insert the story prompt into the art guide.
...
The art guide now optionally supports the sequence <|>
If this exists in the art guide, <|> is replaced by the story summary.
Otherwise, the art guide is appended to the summary as before.
Update the default art guide to place the medium before the summary.
Also update the art guide tooltip to include the new default.
2023-01-01 21:12:25 -08:00
somebody
34c13ee760
Track who wrote original action
2022-12-27 21:20:07 -06:00
somebody
0a6dd8f7d8
Add prompt "support"
2022-12-27 18:52:22 -06:00
somebody
e772860d18
Add endpoint to get action composition
2022-12-27 17:33:46 -06:00
somebody
941f86145e
Track original text
2022-12-27 16:36:28 -06:00
somebody
901322b66b
Make settings work
2022-12-27 15:22:57 -06:00
somebody
7ff6c409f7
Fix probabilities on UI1
2022-12-21 17:23:35 -06:00
ebolam
99135acdea
Don't save host flag
2022-12-21 14:09:09 -05:00
ebolam
1409682427
Fix for some UI1 syncing issues
2022-12-21 13:41:59 -05:00
ebolam
bc9249adfc
Added one time warning system (Currently used to warn users of new save format)
2022-12-21 12:22:26 -05:00
ebolam
7521091e7c
Changed alt_multi_gen to experimental and UI2 only
2022-12-21 10:25:50 -05:00
ebolam
cd24766bf0
Fix for horde bridge folder rename
2022-12-21 08:38:44 -05:00
ebolam
c0f5a712ed
updating submodule
2022-12-21 08:14:13 -05:00
ebolam
5df401f56e
Fix for Original UI model load status box not disapearing after loading
...
Fix for gpt2 model load error
Moved horde bridge to a thread using modified bridge code (will be broken until push is accepted into db0's git)
2022-12-20 20:35:21 -05:00
ebolam
72281ea082
Fix for default model settings
2022-12-20 18:43:14 -05:00
ebolam
0744dea49d
Fix for pictures
2022-12-20 11:41:59 -05:00
ebolam
0983042953
Merge branch 'UI2' of https://github.com/ebolam/KoboldAI into UI2
2022-12-18 13:32:46 -05:00
ebolam
b5c39cf012
Minor fix
2022-12-18 13:32:41 -05:00
ebolam
8105de58a2
Set auto spacing to true by default
2022-12-18 11:14:56 -05:00
ebolam
c46dd588be
Fix for resetting models
2022-12-18 11:11:51 -05:00
somebody
2a556ea346
small commentator + WI image overhaul
2022-12-17 16:23:39 -06:00
ebolam
df23399a4a
Merge pull request #346 from one-some/ui2-fix-topk
...
Fix top-k and shortcuts
2022-12-16 21:18:36 -05:00
ebolam
c3438268e9
Fix for Original UI to use new save formats/code
2022-12-16 21:17:25 -05:00
somebody
9e6dcc7d6a
Fix top-k
2022-12-16 19:56:36 -06:00
ebolam
802bef8c37
Bug fix for probabilities (fixes issue 344)
2022-12-16 20:05:15 -05:00
ebolam
eabbd73bf3
Potential fix for setting action data crash (Issue 343)
2022-12-16 20:02:29 -05:00
ebolam
72c0a54f4e
Fix for probabilities code
2022-12-16 19:50:13 -05:00
ebolam
248994a610
Copy Paste Fix
2022-12-15 21:11:46 -05:00
ebolam
8dba339155
tweaked simple mode settings
2022-12-14 18:43:47 -05:00
ebolam
a7a6c10f6e
Added in image generation for actions (clicking on text will swap image to that generation)
2022-12-14 14:29:51 -05:00
ebolam
50f9508ee7
Merge branch 'UI2' of https://github.com/ebolam/KoboldAI into UI2
2022-12-14 09:21:40 -05:00
