qwen2_5_omni_guardrail

boyuzhuGPT/qwen2_5_omni_guardrail

qwen2_5_omni_guardrail 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

13% of all-time downloads

All-time downloads

169

Public

Parameters

8.9B

518 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 8, 2025
Updated: Oct 8, 2025
SHA: 4785797d

Model card

From the Hugging Face model README

qwen2_5_omni_guardrail

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

Loss: 0.6665
Token Acc: 0.7955

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: 7
gradient_accumulation_steps: 4
total_train_batch_size: 56
total_eval_batch_size: 7
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
0.9021	0.1039	50	0.9205	0.7297
0.9695	0.2078	100	0.9952	0.7195
0.9601	0.3117	150	0.9734	0.7263
0.9378	0.4156	200	0.9595	0.7289
0.9390	0.5195	250	0.9449	0.7318
0.8926	0.6234	300	0.9310	0.7358
0.9051	0.7273	350	0.9156	0.7394
0.8859	0.8312	400	0.8981	0.7417
0.8712	0.9351	450	0.8760	0.7477
0.7780	1.0374	500	0.8808	0.7480
0.7604	1.1413	550	0.8487	0.7548
0.7572	1.2452	600	0.8360	0.7574
0.7331	1.3491	650	0.8217	0.7601
0.7224	1.4530	700	0.8031	0.7632
0.7041	1.5569	750	0.7866	0.7666
0.7000	1.6608	800	0.7697	0.7708
0.6760	1.7647	850	0.7534	0.7746
0.6628	1.8686	900	0.7397	0.7772
0.6366	1.9725	950	0.7249	0.7802
0.5454	2.0748	1000	0.7189	0.7826
0.5519	2.1787	1050	0.7049	0.7860
0.5499	2.2826	1100	0.6966	0.7884
0.5468	2.3865	1150	0.6902	0.7904
0.5225	2.4904	1200	0.6791	0.7925
0.5161	2.5943	1250	0.6749	0.7939
0.5306	2.6982	1300	0.6707	0.7944
0.4990	2.8021	1350	0.6682	0.7950
0.5109	2.9060	1400	0.6666	0.7954
0.5278	3.0	1446	0.6665	0.7955

Framework versions

Transformers 4.57.0.dev0
Pytorch 2.8.0+cu128
Datasets 4.1.1
Tokenizers 0.22.1

Task: Text-to-Audio
Library: transformers
Type: qwen2_5_omni
Created: Oct 8, 2025
Updated: Oct 8, 2025