ONNX Model Zoo

jhpassion0621/kp-mt5-base

By jhpassion0621 · ↓ 0 · ♥ 0 · Updated 2025-09-23

What's in this repo

This page lists the files in jhpassion0621/kp-mt5-base, including decoder_model_merged_quantized.onnx, encoder_model_quantized.onnx.

  • 2 ONNX models (.onnx files)
  • 18 files, including 11 .json, 2 .onnx, 1 .md, 1 .safetensors, 1 .model, 1 .bin
  • Last updated 2025-09-23

ONNX files

File Size Download
onnx/decoder_model_merged_quantized.onnx — Download
onnx/encoder_model_quantized.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

kp-mt5-base

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9680
  • Bleu: 29.4263
  • Gen Len: 44.3157

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: 2.59e-05
  • train_batch_size: 24
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 96
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Bleu Gen Len Validation Loss
1.8289 0.4026 20001 17.9948 45.585 1.3952
1.569 0.8052 40002 22.2856 45.2362 1.2204
1.463 1.2078 60003 24.6884 44.4264 1.1352
1.3552 1.6104 80004 26.0272 44.3574 1.0864
1.3187 2.0130 100005 27.0619 45.005 1.0543
1.3011 2.4156 120006 1.0286 27.63 44.1082
1.2552 2.8182 140007 0.9847 29.0405 44.4054

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.0

Model info

transformers
transformers onnx safetensors mt5 text2text-generation generated_from_trainer base_model:google/mt5-base base_model:quantized:google/mt5-base license:apache-2.0 endpoints_compatible region:us
↓ 0 ♥ 0

Created: 2025-09-18

Updated: 2025-09-23

View on Hugging Face

Files (18)

.gitattributes
README.md
config.json
generation_config.json
model.safetensors
onnx/config.json
onnx/decoder_model_merged_quantized.onnx ONNX
onnx/encoder_model_quantized.onnx ONNX
onnx/generation_config.json
onnx/ort_config.json
onnx/special_tokens_map.json
onnx/tokenizer.json
onnx/tokenizer_config.json
special_tokens_map.json
spiece.model
tokenizer.json
tokenizer_config.json
training_args.bin

Related models

More from jhpassion0621

More models

No task type declared.

Popular models