qwen2_5_omni_all_1016

boyuzhuGPT/qwen2_5_omni_all_1016

qwen2_5_omni_all_1016 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

8% of all-time downloads

All-time downloads

315

Public

Parameters

8.9B

482 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors17.9 GB · 100%

At a glance

Task: Text-to-Audio
Library: transformers
Model type: qwen2_5_omni
Access: Public
Created: Oct 16, 2025
Updated: Oct 16, 2025
SHA: 94a2edfe

Model card

From the Hugging Face model README

qwen2_5_omni_all_1016

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6546
Token Acc: 0.7991

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Token Acc
0.8879	0.1112	50	0.9205	0.7307
0.9361	0.2223	100	0.9695	0.7251
0.9143	0.3335	150	0.9582	0.7284
0.9061	0.4447	200	0.9360	0.7338
0.9164	0.5559	250	0.9249	0.7373
0.8928	0.6670	300	0.9032	0.7426
0.8861	0.7782	350	0.9465	0.7387
0.8532	0.8894	400	0.8842	0.7466
0.8425	1.0	450	0.8555	0.7530
0.7430	1.1112	500	0.8398	0.7562
0.7212	1.2223	550	0.8253	0.7598
0.7343	1.3335	600	0.8107	0.7628
0.7036	1.4447	650	0.7920	0.7658
0.6966	1.5559	700	0.7733	0.7702
0.6805	1.6670	750	0.7599	0.7727
0.6592	1.7782	800	0.7404	0.7773
0.6510	1.8894	850	0.7213	0.7818
0.6150	2.0	900	0.7080	0.7849
0.5527	2.1112	950	0.6994	0.7874
0.5414	2.2223	1000	0.6898	0.7909
0.5015	2.3335	1050	0.6823	0.7930
0.5122	2.4447	1100	0.6704	0.7955
0.5033	2.5559	1150	0.6639	0.7968
0.4931	2.6670	1200	0.6587	0.7981
0.5119	2.7782	1250	0.6563	0.7990
0.5115	2.8894	1300	0.6549	0.7989
0.5185	3.0	1350	0.6546	0.7991

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.22.1

Task: Text-to-Audio
Library: transformers
Type: qwen2_5_omni
Created: Oct 16, 2025
Updated: Oct 16, 2025