Downloads · 30 days
37
59% of all-time downloads
boyuzhuGPT/qwen2_5_omni_all_1015_wo_audio
qwen2_5_omni_all_1015_wo_audio is a text-to-audio model from boyuzhuGPT. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
37
59% of all-time downloads
All-time downloads
63
Public
Parameters
8.9B
447 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17.9 GB · 100%
From the Hugging Face model README
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Token Acc |
|---|---|---|---|---|
| 0.9035 | 0.1235 | 50 | 0.9303 | 0.7264 |
| 0.9639 | 0.2469 | 100 | 0.9595 | 0.7263 |
| 0.9271 | 0.3704 | 150 | 0.9436 | 0.7292 |
| 0.9139 | 0.4938 | 200 | 0.9303 | 0.7340 |
| 0.8831 | 0.6173 | 250 | 0.9085 | 0.7398 |
| 0.8678 | 0.7407 | 300 | 0.8973 | 0.7410 |
| 0.8481 | 0.8642 | 350 | 0.8721 | 0.7465 |
| 0.8405 | 0.9877 | 400 | 0.8632 | 0.7482 |
| 0.7477 | 1.1111 | 450 | 0.8376 | 0.7551 |
| 0.7283 | 1.2346 | 500 | 0.8215 | 0.7583 |
| 0.7169 | 1.3580 | 550 | 0.8048 | 0.7616 |
| 0.7011 | 1.4815 | 600 | 0.7884 | 0.7666 |
| 0.6865 | 1.6049 | 650 | 0.7673 | 0.7700 |
| 0.6773 | 1.7284 | 700 | 0.7466 | 0.7744 |
| 0.6495 | 1.8519 | 750 | 0.7298 | 0.7775 |
| 0.6359 | 1.9753 | 800 | 0.7114 | 0.7819 |
| 0.5476 | 2.0988 | 850 | 0.7051 | 0.7854 |
| 0.5545 | 2.2222 | 900 | 0.6890 | 0.7883 |
| 0.5256 | 2.3457 | 950 | 0.6809 | 0.7903 |
| 0.5741 | 2.4691 | 1000 | 0.6723 | 0.7922 |
| 0.5286 | 2.5926 | 1050 | 0.6659 | 0.7937 |
| 0.5133 | 2.7160 | 1100 | 0.6612 | 0.7949 |
| 0.4898 | 2.8395 | 1150 | 0.6593 | 0.7951 |
| 0.5075 | 2.9630 | 1200 | 0.6582 | 0.7952 |
| 0.4914 | 3.0 | 1215 | 0.6582 | 0.7953 |