Henk
33969b5845
Basic HF code execution support
2023-05-05 17:23:01 +02:00
somebody
efe268df60
Move overrides to better places
2023-05-02 20:18:33 -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
onesome
467f2f25eb
More loading fixes
2023-04-26 16:58:33 -05:00
onesome
9579298df7
Better fallback
2023-04-25 22:28:07 -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
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
77f0797b1a
Model fix
2023-04-02 15:47:52 -05:00
somebody
9d70646e4d
Lazyload: Safetensors
2023-04-02 15:40:34 -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
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
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
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
