Summarization
Transformers
PyTorch
Safetensors
Korean
t5
text2text-generation
T5
text-generation-inference
Instructions to use eenzeenee/t5-base-korean-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eenzeenee/t5-base-korean-summarization with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="eenzeenee/t5-base-korean-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("eenzeenee/t5-base-korean-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("eenzeenee/t5-base-korean-summarization") - Notebooks
- Google Colab
- Kaggle
Adding ONNX file of this model
#2
by mrm8848 - opened
- onnx/config.json +34 -0
- onnx/decoder_model.onnx +3 -0
- onnx/encoder_model.onnx +3 -0
- onnx/generation_config.json +8 -0
onnx/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "onnx/eenzeenee/t5-base-korean-summarization/checkpoint-500",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"T5ForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 2048,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 0,
|
| 12 |
+
"dense_act_fn": "gelu_new",
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"eos_token_id": 1,
|
| 15 |
+
"feed_forward_proj": "gated-gelu",
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"max_length": null,
|
| 21 |
+
"model_type": "t5",
|
| 22 |
+
"num_decoder_layers": 12,
|
| 23 |
+
"num_heads": 12,
|
| 24 |
+
"num_layers": 12,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.49.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 50358
|
| 34 |
+
}
|
onnx/decoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8295fd5c9acf1f8d54d4d3f9a6a2d13c7eb0268f104c3a2af34469b9c9f3e9c
|
| 3 |
+
size 762868856
|
onnx/encoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:214181ccc56e564a87ba13ddd588c13848d71353c667a41eacbf5ccdd4a26592
|
| 3 |
+
size 494704328
|
onnx/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.49.0"
|
| 8 |
+
}
|