9f79e11bb5
Remove legacy presets
2023-09-06 14:19:50 +03:00
0136abe8ef
removed streaming_kobold from kobold presets
2023-08-26 15:15:48 +02:00
c170ecd6f0
removed storywriter-llama2 kobold preset
2023-08-26 14:15:23 +02:00
7fcdd4563f
ported 3 textgen presets to kobold
2023-08-26 14:01:35 +02:00
73f9117bea
Update KoboldAI Deterministic.settings
...
After extensive testing, I've adjusted repetition penalty slightly to be the same as simple-proxy-for-tavern's default preset and ooba's LLaMA-Precise settings preset. This fixed some models talking/acting as User.
2023-08-13 19:25:56 +02:00
c4602df108
kobold-presets-without-max_length+genamt
2023-08-06 21:59:57 +02:00
1f56f0d64a
Update simple-proxy-for-tavern.settings
...
Go back down to 2048 tokens instead of 4096 to be in line with the other non-Llama 2-specific presets
2023-08-03 11:47:59 +02:00
905131c764
Update Deterministic.settings
...
Go back down to 2048 tokens instead of 4096 to be in line with the other non-Llama 2-specific presets
2023-08-03 11:46:53 +02:00
7dfaf6f0b0
Fix Storywriter-Llama2.settings
...
Removed "can_use_streaming" since that should be determined by SillyTavern and not be hardcoded in the preset.
2023-08-02 18:06:06 +02:00
3f015f4bd2
Fix Deterministic.settings
...
Removed "can_use_streaming" since that should be determined by SillyTavern and not be hardcoded in the preset.
2023-08-02 18:05:27 +02:00
6f18c457fc
simple-proxy-for-tavern default preset
...
These are the same settings as [simple-proxy-for-tavern's default preset](https://github.com/anon998/simple-proxy-for-tavern/blob/main/presets/default.json ). I've fixed the sampler order and raised the context size to Llama 2's 4096 tokens.
2023-08-02 18:03:14 +02:00
32f605e413
Llama-2-KoboldAI-presets
...
Here are two presets I've found very useful for Llama 2-based models:
- Deterministic takes away the randomness and is good for testing/comparing models because same input equals same output.
- Storywriter-Llama2 is the Storywriter preset adjusted for Llama 2's 4K context size. It also works well against Llama 2's repetition/looping issues.
2023-08-01 23:13:37 +03:00
e9288874b1
Update RR preset
2023-07-23 22:09:59 +03:00
edd41989fd
Initial commit
2023-07-20 20:32:15 +03:00
Cohee
Stefan Daniel Schwarz
SDS
Cohee