|
|
c09133d00f
|
added safetensors support (with metadata) and feed whatever torch.load/torch.save into it
|
2024-08-03 23:15:20 -05:00 |
|
|
|
6a733eb2ed
|
changed torch.Tensor().to(device, dtype) to just torch.tensor(..., device, dtype) because it's been bothering my autism that I'm creating tensors then converting rather than creating with the right device/dtype, some 'optimization' to compile the model but it doesnt seem to do anything useful
|
2024-08-03 22:10:21 -05:00 |
|
|
|
11fa3da665
|
some cleanup, fixed the wrapper attention to explicitly use other sdpa backends
|
2024-08-03 19:51:00 -05:00 |
|
|
|
c9ec6b28ef
|
it actually wasn't working because Engines.__init__() automatically moves the entire module to the requested device, which was being called after offloading the model in the test trainer (and it seems I cant do it without injecting a bunch of shit in modeling_llama.py)
|
2024-08-01 20:56:28 -05:00 |
|
|
|
b4c895114c
|
naive model offloading support (handles automatically splitting parts of the model to requested device per memory constraints, either inferred or requested in the yaml, input tensors are automatically migrated to the right device, it SEEMS to work for training under the test trainer when split between GPU and CPU) (this was specifically only because that Flux imagegen model released so I can test it there)
|
2024-08-01 20:12:06 -05:00 |
|
|
|
387358bc8a
|
fixes for the NAR-len model, and documentation some config options, and a better way to handle resizing modules on state_dict load
|
2024-07-31 20:35:09 -05:00 |
|
|
|
52d13b321f
|
I rather have it default to non-strict loading instead so I can clean up YAMLs
|
2024-07-30 22:24:38 -05:00 |
|
|
|
07f8e2ad06
|
added option to set the causal size (how many tokens to sample per AR step), but requires the model to be trained for this (which explains why recurrent chunk sampling just doesn't work for the retnet tests, obvious in hindsight)
|
2024-07-30 20:53:51 -05:00 |
|
|
|
682e4387dc
|
oops (fixed proms being erased from a config oversight)
|
2024-07-25 12:39:57 -05:00 |
|
|
|
1acb0e9c84
|
added experimental training setting to perform token dropout to MAYBE compensate for errors from the preceding RVQ level (two types: token error offset, token dropout embedding replace)
|
2024-07-24 19:35:17 -05:00 |
|
|
|
75b04686f8
|
added prom-less training / inferencing, some other things
|
2024-07-22 19:36:07 -05:00 |
|
|
|
e19aa643a6
|
cleaned up demo page creation, added option to pass in RVQ level sampling distribution for training
|
2024-07-21 19:12:03 -05:00 |
|
|
|
d53038a9e4
|
actually have split classifiers working
|
2024-07-19 15:33:31 -05:00 |
|
|
|
83a0954f85
|
fixes for re-introducing SpeechX tasks (need to actually validate if these all do the right things)
|
2024-07-18 17:16:32 -05:00 |
|
|
|
bccbb77a1a
|
added option to either naively concat codes to concat audio waveforms (prior behavior) or to decode => concat => encode instead (although this only currently happens for prom sampling if an utternace is too small)
|
2024-07-18 16:48:41 -05:00 |
|
|
|
97e768601c
|
re-introducing SpeechX tasks (need to validate them all, everything works with base tts anyways)
|
2024-07-18 16:16:14 -05:00 |
|
|
|
22fe53508c
|
added experimental disjointed position IDs (because I *think* this might help because technically a sequence is made up of several parts, and the position embeddings shouldn't be unified)
|
2024-07-16 19:52:41 -05:00 |
|
|
|
fe0f235335
|
mechanism to store the model config inside the weights and load them, some other things to allow LoRA training on the RetNet (gradient checkpointing will gripe about inputs not having require_grad and nothing seems to remedy it)
|
2024-07-16 18:23:13 -05:00 |
|
|
|
3acc54df22
|
allow loading a different model within the web ui (apparently I did not have the web UI in the documentation)
|
2024-07-15 19:59:48 -05:00 |
|
|
|
7b210d9738
|
sanity cleanup
|
2024-07-04 15:58:08 -05:00 |
|
|
|
1ecf2793f4
|
(commented-out) support for facebookresearch/AudioDec, but support really didn't wow me (so I commented it out until I figure out why my output audio is super crusty with AudioDec)
|
2024-07-04 15:40:51 -05:00 |
|
|
|
f770467eb3
|
stuff
|
2024-07-01 18:13:29 -05:00 |
|
|
|
312a8e3ead
|
add shuffle to samplers that can support it
|
2024-06-30 11:36:46 -05:00 |
|
|
|
396af541c5
|
ugh
|
2024-06-30 11:11:58 -05:00 |
|
|
|
dced595391
|
more cleanup
|
2024-06-30 11:00:12 -05:00 |
|
|
|
bc2a6fa756
|
sanity cleanup: moved experimental features under its own thing
|
2024-06-30 10:37:33 -05:00 |
|
|
|
2808f881c8
|
cleaned up subjugated audio embedding into a flag, flag can also have it include the original, underlying embedding as well (it seems to do better when set to inclusive)
|
2024-06-29 21:46:35 -05:00 |
|
|
|
ec5eaebcbc
|
experimental method of using DACs quantizer ""embeddings"" to see if it helps with model quality
|
2024-06-29 19:46:11 -05:00 |
|
|
|
83075c1505
|
sort duration buckets to ensure that paths sorted-by-duration are actually sorted by duration (because i didnt know that python dicts can have non-strings as keys), added batching samples based on total duration to ensure best training throughput
|
2024-06-28 22:28:54 -05:00 |
|
|
|
8fffb94964
|
backport fix from tortoise_tts with local trainer + loading state when training lora
|
2024-06-25 13:41:29 -05:00 |
|
|
|
62a53eed64
|
fixed deducing tokenizer path, added option to default to naive tokenizer (for old models, like ar+nar-retnet-8)
|
2024-06-18 22:11:14 -05:00 |
|
|
|
8a986eb480
|
load exported LoRA weights if exists (to-do: make a better LoRA loading mechanism)
|
2024-06-18 21:45:46 -05:00 |
|
|
|
7cfb78fa64
|
enable LoRA for targetted RVQ levels (to experiment with, seems to help)
|
2024-06-17 21:45:03 -05:00 |
|
|
|
1d159b1476
|
updated export routine to split LoRA weights from the state dict (should work with deepspeed)
|
2024-06-17 13:28:18 -05:00 |
|
|
|
bd0bc10ec0
|
added LoRA policy to decide what layer of the model gets adapted based on simple inclusion/exclusion terms
|
2024-06-17 13:05:06 -05:00 |
|
|
|
45a39fb79f
|
very rudimentary lora support (no deepspeed support, tested training and saving but not loading yet)
|
2024-06-17 00:09:16 -05:00 |
|
|
|
b3b67f34ac
|
added option to sort paths by durations to better group equally lengthed sequences together (and there was maybe a logic error from creating the samplers and then interleave-reordering paths, desyncing them, maybe)
|
2024-06-13 22:37:34 -05:00 |
|
|
|
65a8960305
|
option to split classifier per-level instead of sharing one (at this point I'm just scrambling to try and cope with training a DAC model, the NAR is being a pain)
|
2024-06-11 22:28:59 -05:00 |
|
|
|
a7a6e0ac76
|
validated that inferencing works, changed some defaults (NAR benefits from greedy sampling)
|
2024-06-09 17:11:38 -05:00 |
|
|
|
132a02c48b
|
sanity cleanup, backup config yaml for each log file
|
2024-06-09 11:22:52 -05:00 |
|
|
|
58fb0a84db
|
added experimental NAR only model (inferences text length, need more experimenting), AudioEmbedding logic cleanup (I still think it's being done wrong)
|
2024-06-08 15:42:02 -05:00 |
|
|
|
e35a91c67a
|
ugh
|
2024-06-07 21:56:14 -05:00 |
|
|
|
eafa622be2
|
I forgot the actual reason I was cleaning things up was to re-include prom loss calculation (I realized the reason I did this was because of an prom embedding oversight, it seems to work now)
|
2024-06-07 20:29:25 -05:00 |
|
|
|
da8242d086
|
finally got around to removing omegaconf
|
2024-06-07 20:23:53 -05:00 |
|
|
|
b2194b859a
|
re-added loading multiple models because I'm now entertaining having split AR/NAR models again (and need a way to load both at once)
|
2024-06-06 09:48:43 -05:00 |
|
|
|
4073656293
|
oops
|
2024-06-05 20:53:10 -05:00 |
|
|
|
48cd1054f9
|
madness
|
2024-06-04 23:48:51 -05:00 |
|
|
|
406ff7bbe1
|
re-implemented config.model.interleave for the HF-compat experimental method
|
2024-06-04 14:19:52 -05:00 |
|
|
|
934672252b
|
feverish cleanup
|
2024-06-03 21:28:49 -05:00 |
|
|
|
c1fcd889d5
|
reverted automatically disabling split loss calc, since it seems that it's actually cacling loss on prom causes the oddities, maybe
|
2024-06-01 12:34:59 -05:00 |
|
|
|
31785f4eeb
|
actually don't default to compute split losses, test bitnet model doesn't seem to be doing things right (despite debug printouts showing theyre roughly the same logit/loss sequences, could just be bitnet linears being not up to par on actual models)
|
2024-06-01 09:12:51 -05:00 |
|
|
|
e9c87060df
|
oops
|
2024-05-31 22:22:28 -05:00 |
|
|
|
b482ca19ff
|
added model config option to set KV head count for MQA/GQA instead of MHA for llama-based models (i think its very negligible both ways on such a small model size)
|
2024-05-31 19:32:37 -05:00 |
|
|
|
da473295b7
|
better way to compute per-segment losses
|
2024-05-28 19:29:54 -05:00 |
|
|
|
5af6f41c94
|
added loss calcs against prom (requires the right settings for not shit results, disabled by default)
|
2024-05-27 08:43:00 -05:00 |
|
|
|
ddbacde0d1
|
DAC just doesn't work well enough......
|
2024-05-25 11:07:52 -05:00 |
|
|
|
458b95d196
|
added option to split between text loss and audio loss (to-do: document this better), because it may or may not be a problem with LLaMA-backed models because my loss hovers around 3.9 / 56% accuracy despite sounding decent at the moment
|
2024-05-19 11:23:56 -05:00 |
|
|
|
8d79f78e0a
|
god I need to replace omegaconf
|
2024-05-12 14:01:52 -05:00 |
|
|
|
2437a86efa
|
ugh
|
2024-05-12 13:02:15 -05:00 |
|
|
|
3774fcbdee
|
ugh
|
2024-05-11 22:58:38 -05:00 |
|
|
|
856545f8bb
|
nan loss detection (should have added it earlier), loss scaling for local backend + fp16
|
2024-05-11 22:23:29 -05:00 |
|
|
|
3337c69e5a
|
leverage between xformers and torch.backends.cuda.sdp_kernel for attention
|
2024-05-11 17:14:05 -05:00 |
|
|
|
0b6499601b
|
sanitizing
|
2024-05-11 16:31:05 -05:00 |
|
|
|
04a80d6b55
|
maybe it's better to be more explicit in deepspeed configs
|
2024-05-11 13:57:43 -05:00 |
|
|
|
4d93a16ef7
|
might just be better to explicitly define prompt duration ranges, especially under a "train small contexts then increase it" training paradigm
|
2024-05-11 09:50:54 -05:00 |
|
|
|
1547de5020
|
haha...
|
2024-05-09 23:15:52 -05:00 |
|
|
|
b7bd885651
|
some possible sanity with deepspeed config
|
2024-05-09 22:48:42 -05:00 |
|
|
|
b6131565ad
|
autotune?
|
2024-05-09 21:25:40 -05:00 |
|
|
|
6ed6ab8c03
|
a bit more cleanup for deepspeed ds_cfg creation
|
2024-05-09 21:00:26 -05:00 |
|
|
|
0d5d545a40
|
crammed in DAdaptation (doesn't seem worth it) and ScheduleFree (forgot I wanted to weeks ago, seems promising), optimization wrapper cleanup, test trainer changes, etc.
|
2024-05-09 20:28:20 -05:00 |
|
|
|
215800484d
|
correcting my wrong of assuming I could just use raw 24Khz audio in the 44Khz DAC without too much of an issue (there are issues)
|
2024-05-04 23:49:15 -05:00 |
|
|
|
33b7f81b94
|
small cleanups
|
2024-05-04 22:37:22 -05:00 |
|
|
|
ffa200eec7
|
added option to specify frames per second for the given audio representation (Encodec is 75Hz, DAC is 41Hz (at 24K sources))
|
2024-05-04 12:05:41 -05:00 |
|
|
|
c494894261
|
simple DDP wrapper (for my NVlink test)
|
2024-05-04 11:48:26 -05:00 |
|
|
|
a7b43b98b5
|
renamed cfg.bitsandbytes to cfg.optimizations (and having it serve as cfg.optimizations.bitsandbytes)
|
2024-05-02 20:08:59 -05:00 |
|
|
|
b5d1456a09
|
backwards compat for my shitty old weights (was testing if disabling AudioEmbedding summing magically made things better (it did not))
|
2024-04-29 22:14:01 -05:00 |
|
|
|
5120ffdda7
|
god it would be nice to know the best way to handle audio embeddings, because I genuinely don't know without skimming through papers or devoting X amount of GPU hours in training
|
2024-04-29 18:24:05 -05:00 |
|
|
|
caad7ee3c9
|
final tweaks, hopefully
|
2024-04-28 22:28:29 -05:00 |
|
|
|
071fb97777
|
dataset preparation script updates, caved and am using HF tokenizer now
|
2024-04-21 14:49:18 -05:00 |
|
|
|
a8ffa88844
|
it slipped my mind that technically DAC can be used at any sample rate, since it models waveforms; make it a config YAML option to allow this behavior
|
2024-04-19 18:36:54 -05:00 |
|
|
|
4f5c9e518a
|
actually use the passed-through sample rate from encode for DAC because it does its own resampling I guess
|
2024-04-18 13:32:41 -05:00 |
|
|
|
5ff2b4aab5
|
finally swallowing the Descript-Audio-Codec pill (I guess I'm going to have to regenerate my entire dataset)
|
2024-04-17 20:39:35 -05:00 |
|
|
|
b0bd88833c
|
refractor cleanup, had a revelation on how I can handle a batch of varying tasks
|
2024-04-16 21:04:48 -05:00 |
|
|
|
aa1e25fbf5
|
backwards compat for old YAMLs with models, option to set flash attention 2 for Llama (and derivatives), included syncdoth/RetNets torchscale retnet for shits and grins, etc.
|
2024-04-16 10:02:31 -05:00 |
|
|
|
545162195b
|
deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things
|
2024-04-15 19:54:32 -05:00 |
|
|
|
789bb5d11b
|
add an optional label override for model loading (used for easy testing between 12/16/20/24 layered model)
|
2024-04-13 12:43:35 -05:00 |
|
|
|
f0c4baeb25
|
added Adagrad (experimenting with it), added 'extended' model size (16 layers instead of 12, experimenting with it)
|
2024-04-09 22:04:01 -05:00 |
|
|
|
9d97eb5104
|
added FP8 support through NVIDIA/TransformerEngine, added RetNet_HF through syncdoth/RetNet (as an alternative to branch away from torchscale)
|
2024-04-08 20:14:51 -05:00 |
|
|
|
7075c2a5f0
|
added an option to allow injecting embeddings from another model, because it dawned upon me how valuable embeddings from a good model can be for subsequent trainings (defined under cfg.models._embeddings as a relative path to the yaml)
|
2024-04-04 19:11:49 -05:00 |
|
|
|
47435207f7
|
Added cfg.bitsandbytes.replace as a less intrusive alternative to cfg.bitsandbytes.inject to replace all Linear modules in a model
|
2024-03-01 19:20:10 -06:00 |
|
|
|
0427d8d076
|
logger broke for some reason, added flag to just tqdm.write instead, make cfg.bitsandbytes.bitnet==True yamls denoted since I'm sure they're not interoperable
|
2024-03-01 10:32:35 -06:00 |
|
|
|
35d78a2bb0
|
Yet Another Underlying Transformer Implementation (BitNet, will give it a few days to see how it fares)
|
2024-02-29 20:29:17 -06:00 |
|
|
|
c690aa509d
|
fixes and compat (MoE-fying an existing model and retraining from there just ruins it after a second of audio...)
|
2023-12-25 21:20:32 -06:00 |
|
|
|
9c198eb75a
|
added torchscale XMOE integration (because Mixtral 8x7B seems very promising and I want to see if it works)
|
2023-12-20 18:45:58 -06:00 |
|
|
|
32d4271ca8
|
fixed issue with training from scratch (oops)
|
2023-10-21 09:55:38 -05:00 |
|
|
|
3195026dba
|
fixed issue with the 'add another target audio to artificially create longer sequences' for HDF5 just duplicating the utterance initially sampled
|
2023-10-18 20:38:33 -05:00 |
|
|
|
65f500083d
|
tweaks to try and get deepspeed quantized inferencing, validating bitsandbytes and deepspeed quantization, nothing seems to work
|
2023-10-12 22:21:43 -05:00 |
|
|
|
8740cdefc6
|
added initial support for languages (still testing, marked as model version 3), added experimental 'context extend by limiting the resp context' (untested)
|
2023-10-11 20:38:40 -05:00 |
|
|
|
6045cbce94
|
added experimental option to append utterances for training target (emphasis on experimental)
|
2023-10-11 17:32:45 -05:00 |
|
|
|
893a610fad
|
cleanup, use deepspeed inferencing pathway if requested
|
2023-10-09 15:24:04 -05:00 |
|
