mrq
16 Followers · 0 Following

  • https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.

    XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG

  • Joined on Oct 10, 2022
Repositories
18
 Projects Packages Public Activity Starred Repositories
Loading Heatmap…

mrq pushed to master at mrq/ai-voice-cloning

2024-04-28 01:08:12 +07:00

mrq commented on issue mrq/ai-voice-cloning#484

So is this abandoned?

> So is this abandoned? Pretty much. The *extremely short* of it, is that this repo itself is in dire need of a rewrite. > If it is dead, anyone have suggestions on replacements with a UI…

2024-04-28 01:01:37 +07:00

mrq pushed to master at mrq/vall-e

  • 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)
  • 91062361af tweaks
  • f3c59c3e7e cleaner replacement code (because I realized BitNet had an implementation for it too), added calculating gradient norm and performing gradient clipping in local trainer (non-deepspeed)
  • 47435207f7 Added cfg.bitsandbytes.replace as a less intrusive alternative to cfg.bitsandbytes.inject to replace all Linear modules in a model
  • 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
  • Compare 13 commits »

2024-04-08 19:44:29 +07:00

mrq pushed to master at mrq/vee-speedrun-ratings

2024-02-24 23:16:06 +07:00

mrq pushed to master at mrq/vee-speedrun-ratings

2024-02-24 23:06:26 +07:00

mrq pushed to master at mrq/vee-speedrun-ratings

2024-01-21 06:22:15 +07:00

mrq pushed to master at mrq/vall-e

  • 6c51a629cc resetting step count resets the samples processed and other metrics

2023-10-29 17:10:30 +07:00

mrq pushed to master at mrq/vall-e

  • 0aa2a3cc07 evaluation/validation passes language ID during training (oops)

2023-10-29 17:00:02 +07:00

mrq pushed to dreamcast at mrq/reactphysics3d

  • f61c6c5713 Dreamcast fixes, also that experimental float16/quantized uint16_t triangle mesh support

2023-10-27 03:39:21 +07:00

mrq created branch dreamcast in mrq/reactphysics3d

2023-10-27 03:37:49 +07:00

mrq pushed to dreamcast at mrq/reactphysics3d

  • 2958d57725 Dreamcast fixes, also that experimental float16/quantized uint16_t triangle mesh support

2023-10-27 03:37:49 +07:00

mrq pushed to master at mrq/reactphysics3d

  • 1332aa7990 Agnostified CMakeList to deduce whether to inject KOS's GCC flags; support for using float16/bfloat16 vertices for triangle mesh

2023-10-27 03:29:51 +07:00

mrq pushed to master at mrq/reactphysics3d

  • 4738a640b0 One of these flags fixes the '__gnu_cxx::__concurrence_lock_error' error on Dreamcast

2023-10-26 19:56:23 +07:00

mrq pushed to master at mrq/reactphysics3d

  • bd94c476a3 Added fallback quantized-float-as-uint16_t for envs without float16 (like KOS's dc-chain)

2023-10-26 18:10:42 +07:00

mrq pushed to master at mrq/reactphysics3d

  • dccb584c82 Agnostified CMakeList to deduce whether to inject KOS's GCC flags; support for using float16/bfloat16 vertices for triangle mesh (experimental)

2023-10-26 16:12:25 +07:00

mrq pushed to master at mrq/reactphysics3d

  • 8ca1798ef9 Agnostified CMakeList to deduce whether to inject KOS's GCC flags; support for using float16/bfloat16 vertices for triangle mesh (experimental)

2023-10-26 14:38:50 +07:00

mrq pushed to master at mrq/ai-voice-cloning

2023-10-24 23:40:04 +07:00

mrq commented on issue mrq/ai-voice-cloning#427

Google Colab Notebook Not Working

> I'm not sure how I would edit the notebook to make it work properly, would I have to update the commands in the repo files or just run the commands inside the colab? If I recall right, there…

2023-10-24 23:21:35 +07:00

mrq commented on issue mrq/ai-voice-cloning#428

Discussions Tab?

You'll need to re-create your training YAML and specifying the `Resume State Path`. It's a bit of a bother with how DLAS requires it to be defined, rather it be automatically deduced.

2023-10-24 20:18:53 +07:00

mrq commented on issue mrq/ai-voice-cloning#428

Discussions Tab?

> because I can't find a discussions tab. Gitea still doesn't really have an analogue to Github's discussion tabs, so the best is just opening issues here and hoping someone else (or I) will…

2023-10-24 18:58:12 +07:00