You're looking at a specific version of this model. Jump to the model overview.
simpletuner /minimax-h3:26348633
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| train_data |
string
|
ZIP or tar of audio/.txt/.lyrics triplets OR videos with .txt captions
|
|
| trigger_word |
string
|
|
Optional instance prompt replacing per-track captions
|
| max_train_steps |
integer
|
1000
Min: 1 Max: 50000 |
Optimizer updates
|
| checkpoint_interval |
integer
|
250
Min: 1 Max: 5000 |
Save every N updates
|
| lora_rank |
integer
|
16
Min: 1 Max: 256 |
LoRA rank
|
| lora_dropout |
number
|
0
Max: 0.5 |
LoRA dropout
|
| learning_rate |
number
|
0.00006
Min: 0.0000001 Max: 0.001 |
Learning rate
|
| resolution |
None
|
480
|
Video pixel-area resolution
|
| video_frames |
None
|
39
|
Video training frames; optional previews use 124 frames
|
| validation_prompt |
string
|
|
Optional prompt rendered at checkpoint saves
|
| validation_lyrics |
string
|
[instrumental]
|
Lyrics for optional validation audio
|
| max_audio_duration |
number
|
30
Min: 3 Max: 300 |
Maximum training audio duration in seconds
|
| enable_regional_compile |
boolean
|
True
|
Compile repeated transformer blocks
|
| attention_mechanism |
None
|
kohaku-fa-auto
|
Attention backend
|
| gradient_checkpointing_interval |
integer
|
2
Min: 1 Max: 16 |
Checkpoint interval in transformer blocks
|
| gradient_checkpointing_segment_stride |
integer
|
4
Min: 1 Max: 64 |
Spacing between checkpointed segments; at least the checkpoint interval
|
| dataloader_prefetch |
boolean
|
True
|
Prepare upcoming training batches in the background
|
| seed |
integer
|
42
|
Training seed
|
| hub_model_id |
string
|
Optional Hugging Face repository for the trained adapter
|
|
| hf_token |
string
|
Write-capable Hugging Face token for uploading the adapter
|
|
| push_checkpoints_to_hub |
boolean
|
True
|
Upload intermediate checkpoints to the Hub in the background
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}