shi-zheng-qxhs/gpt2_oasst2_curated_onnx
By shi-zheng-qxhs · ↓ 4 · ♥ 0 · Updated 2024-02-11
What's in this repo
This page lists the files in shi-zheng-qxhs/gpt2_oasst2_curated_onnx, including decoder_model.onnx, decoder_model_merged.onnx, decoder_model_merged_quantized.onnx and more.
- 6 ONNX models (.onnx files)
- 17 files, including 8 .json, 6 .onnx, 1 .md, 1 .txt
- Last updated 2024-02-11
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | Download |
| onnx/decoder_model_quantized.onnx | — | Download |
| onnx/decoder_with_past_model.onnx | — | Download |
| onnx/decoder_with_past_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
gpt2_oasst2_curated_onnx
This model is a fine-tuned version of gpt2 on sablo/oasst2_curated dataset
Model description
For experimental purpose - chatbot
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0
- optimum 1.13.2
- onnx 1.13.1
- onnxruntime 1.15.1
Model info
Created: 2024-02-08
Updated: 2024-02-11
View on Hugging FaceFiles (17)
Related models
More from shi-zheng-qxhs
No other models by this author.