onesome
bbf4963d6e
Fix custmodpth stuff for hf loading
2023-04-26 16:18:45 -05:00
onesome
c146ae9d84
Delete legacy gpt2 custom loader
2023-04-26 16:07:18 -05:00
onesome
9579298df7
Better fallback
2023-04-25 22:28:07 -05:00
onesome
6e3aebc1ea
Zap debug
2023-04-25 21:13:17 -05:00
onesome
0268305cfe
Change fallback notifications to warnings
2023-04-25 18:26:49 -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
somebody
f9fb5eba89
Remove debug
2023-04-15 18:56:49 -05:00
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
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
2b950f08d3
Remove legacy no accelerate fallback code
...
Was causing issues with disk cache the old code had a
`and not utils.HAS_ACCELERATE` preceding it (a variable which no longer
exists), and since disk cache is accelerate only, there was no disk
handling code in here. Anyway its bad so blast it
2023-04-15 10:47:31 -05:00
Concedo
9705b7b79c
increase API version (+1 squashed commits)
...
Squashed commits:
[c168c08
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
somebody
38c53191d3
possible fix for cache dl thing
2023-04-14 20:25:03 -05:00
somebody
8412f83ce5
Breakmodel: Fix typo
2023-04-03 18:41:18 -05:00
somebody
77f0797b1a
Model fix
2023-04-02 15:47:52 -05:00
somebody
9d70646e4d
Lazyload: Safetensors
2023-04-02 15:40:34 -05:00
somebody
91bb433b5f
GenericTokenizer: Fall back to defined tokenizer
...
Shouldn't be relied on for model-agnostic code, but for loading
processes where you know the tokenizer class used it should be okie
dokie
2023-03-19 19:03:20 -05:00
somebody
ffe85ce8a1
Modeling: Fix logits processors (probs, biasing, lua)
2023-03-17 16:56:47 -05:00
somebody
692dbfeb37
Merge branch 'united' of https://github.com/henk717/KoboldAI into model-structure-and-maybe-rwkv
2023-03-17 16:20:13 -05:00
somebody
8d0bc404a5
Model: More Jax import fixes and formatting
2023-03-17 15:36:44 -05:00
somebody
03af06638c
Modeling: Maybe fix samplers
2023-03-13 20:42:35 -05:00
somebody
b93c339145
Model: Lazyload backends
2023-03-13 20:29:29 -05:00
somebody
938c97b75a
RWKV: Fix yet another typo
2023-03-13 19:39:19 -05:00
somebody
14b2543c7c
RWKV: Fix typo
2023-03-13 19:36:58 -05:00
somebody
b10b201701
Model: Add basic RWKV implementation
2023-03-13 19:34:38 -05:00
somebody
0320678b27
Model: WIP horde and API tests
2023-03-13 14:11:06 -05:00
somebody
cd8ccf0a5e
Modeling: Add seed parameter to raw_generate
...
Yahooo, decoupling from koboldai_vars. This makes the generation test
pass in `test_generation.py`, and makes full determinism outside of
core_generate work.
2023-03-12 21:49:10 -05:00
somebody
8c8bdfaf6a
Model: Fix assorted bugs
...
and ignore warnings in pytest
2023-03-10 20:00:39 -06:00
somebody
3646aa9e83
Model: Respect model lazyload over kaivars
...
kaivars dictates model config unless its from outside aiserver or
whatever.
2023-03-10 20:00:39 -06:00
somebody
52095054a3
Model: Reformat and clean up
2023-03-10 20:00:39 -06:00
somebody
fb0b2f0467
Model: Ditch awful current_model hack
...
thanks to whjms for spotting that this could be zapped
2023-03-10 20:00:38 -06:00
somebody
cb6010d666
Model: Respect sampler bounds in torch
...
A rather embarassing way to spend an hour debugging after I told myself
"I'd better remember to add this important thing to the torch side".
Samplers were being applied when in their "off values" causing
boring mathmatical operations to take place (ie anything x 0 is always
0)
2023-03-07 21:14:37 -06:00
somebody
6b45367cc7
Model: Rename "Colab" to "Basic API"
2023-03-07 17:07:01 -06:00
somebody
dc3dd38c4e
Merge branch 'united' of https://github.com/henk717/KoboldAI into model-structure-and-maybe-rwkv
2023-03-07 17:02:28 -06:00
somebody
3b05359e4b
Model: Refuse to serve certain models over the API
2023-03-07 16:54:08 -06:00
somebody
3a128e76b4
Attempts at dynamic wi fixes
2023-03-07 16:33:23 -06:00
somebody
beef23f5a1
Model: Add debug code for detecting faulty samplers
2023-03-04 19:02:20 -06:00
somebody
b02513df07
Model: Add singleline_stopper and fix stopper code
...
singleline_stopper adapted from MasterAibo in 0ba7ac9
2023-03-04 19:02:20 -06:00
somebody
70cddc46e2
Model: Small cleanup
2023-03-04 19:02:10 -06:00
somebody
27b7635c95
Model: Fix TPU
2023-03-04 19:02:00 -06:00
somebody
54cecd4d5d
Model: And another refactor
2023-03-01 19:16:35 -06:00
