Instructions to use google/mt5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/mt5-small with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/mt5-small") model = AutoModelForSeq2SeqLM.from_pretrained("google/mt5-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Adding ONNX file of this model
Browse filesBeep boop I am the [ONNX export bot 🤖🏎️](https://huggingface.co/spaces/onnx/export). On behalf of [xiongzhongchi](https://huggingface.co/xiongzhongchi), I would like to add to this repository the model converted to ONNX.
What is ONNX? It stands for "Open Neural Network Exchange", and is the most commonly used open standard for machine learning interoperability. You can find out more at [onnx.ai](https://onnx.ai/)!
The exported ONNX model can be then be consumed by various backends as TensorRT or TVM, or simply be used in a few lines with 🤗 Optimum through ONNX Runtime, check out how [here](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models)!
- .gitattributes +2 -0
- onnx/config.json +30 -0
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/encoder_model.onnx +3 -0
- onnx/generation_config.json +7 -0
- onnx/special_tokens_map.json +5 -0
- onnx/spiece.model +3 -0
- onnx/tokenizer.json +3 -0
- onnx/tokenizer_config.json +11 -0
|
@@ -7,3 +7,5 @@
|
|
| 7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
onnx/spiece.model filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
onnx/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 1024,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 8,
|
| 20 |
+
"num_heads": 6,
|
| 21 |
+
"num_layers": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"tokenizer_class": "T5Tokenizer",
|
| 27 |
+
"transformers_version": "4.30.2",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 250112
|
| 30 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fab5238e877bf126662539b7f984b3a2b1d9d44f595b79fe7653f6439215b21
|
| 3 |
+
size 1125417279
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:954a0ef0b71f2e66c13905aea8e805d4af96edcbfc76da3c9db0022791b62a3b
|
| 3 |
+
size 1125648847
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11fd7060e629601625c40050410709ddca1db9695fcd0966827dd7a9e6fd3c5b
|
| 3 |
+
size 1112817305
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703c80852443748cdfd944e3a3eef84d261385dcf934c4827e1acb9f9cea939e
|
| 3 |
+
size 587888181
|
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
|
| 3 |
+
size 16330369
|
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"extra_ids": 0,
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"tokenizer_class": "T5Tokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|