Downloads · 30 days
28
12% of all-time downloads
boyuzhuGPT/qwen2_5_omni_all_1016_3b
qwen2_5_omni_all_1016_3b 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
28
12% of all-time downloads
All-time downloads
243
Public
Parameters
4.7B
141 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors9.4 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 |
|---|---|---|---|---|
| 0.9071 | 0.1112 | 50 | 0.9418 | 0.7258 |
| 0.9224 | 0.2223 | 100 | 0.9557 | 0.7258 |
| 0.8912 | 0.3335 | 150 | 0.9308 | 0.7322 |
| 0.8802 | 0.4447 | 200 | 0.9106 | 0.7362 |
| 0.8884 | 0.5559 | 250 | 0.8947 | 0.7410 |
| 0.8663 | 0.6670 | 300 | 0.8781 | 0.7442 |
| 0.8489 | 0.7782 | 350 | 0.8605 | 0.7484 |
| 0.8120 | 0.8894 | 400 | 0.8461 | 0.7526 |
| 0.8194 | 1.0 | 450 | 0.8331 | 0.7544 |
| 0.7294 | 1.1112 | 500 | 0.8191 | 0.7579 |
| 0.7139 | 1.2223 | 550 | 0.8025 | 0.7617 |
| 0.7250 | 1.3335 | 600 | 0.7911 | 0.7648 |
| 0.6938 | 1.4447 | 650 | 0.7768 | 0.7674 |
| 0.6918 | 1.5559 | 700 | 0.7616 | 0.7710 |
| 0.6794 | 1.6670 | 750 | 0.7497 | 0.7724 |
| 0.6609 | 1.7782 | 800 | 0.7342 | 0.7774 |
| 0.6537 | 1.8894 | 850 | 0.7182 | 0.7808 |
| 0.6221 | 2.0 | 900 | 0.7070 | 0.7831 |
| 0.5732 | 2.1112 | 950 | 0.6991 | 0.7861 |
| 0.5602 | 2.2223 | 1000 | 0.6922 | 0.7887 |
| 0.5291 | 2.3335 | 1050 | 0.6850 | 0.7906 |
| 0.5385 | 2.4447 | 1100 | 0.6763 | 0.7921 |
| 0.5324 | 2.5559 | 1150 | 0.6700 | 0.7939 |
| 0.5214 | 2.6670 | 1200 | 0.6664 | 0.7947 |
| 0.5395 | 2.7782 | 1250 | 0.6650 | 0.7953 |
| 0.5385 | 2.8894 | 1300 | 0.6632 | 0.7955 |
| 0.5408 | 3.0 | 1350 | 0.6629 | 0.7957 |