Instructions to use uzaaft/bart_eli5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use uzaaft/bart_eli5 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("uzaaft/bart_eli5") model = AutoModelForSeq2SeqLM.from_pretrained("uzaaft/bart_eli5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- config.json +2 -2
- generation_config.json +1 -1
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged_quantized.onnx +2 -2
- onnx/decoder_model_quantized.onnx +2 -2
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/decoder_with_past_model_quantized.onnx +2 -2
- onnx/encoder_model.onnx +3 -0
- onnx/encoder_model_quantized.onnx +2 -2
- quantize_config.json +125 -0
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "bart_eli5",
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
|
@@ -57,7 +57,7 @@
|
|
| 57 |
"num_beams": 4
|
| 58 |
}
|
| 59 |
},
|
| 60 |
-
"transformers_version": "4.
|
| 61 |
"use_cache": true,
|
| 62 |
"vocab_size": 50265
|
| 63 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "yjernite/bart_eli5",
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
|
|
|
| 57 |
"num_beams": 4
|
| 58 |
}
|
| 59 |
},
|
| 60 |
+
"transformers_version": "4.33.2",
|
| 61 |
"use_cache": true,
|
| 62 |
"vocab_size": 50265
|
| 63 |
}
|
generation_config.json
CHANGED
|
@@ -5,5 +5,5 @@
|
|
| 5 |
"eos_token_id": 2,
|
| 6 |
"forced_eos_token_id": 2,
|
| 7 |
"pad_token_id": 1,
|
| 8 |
-
"transformers_version": "4.
|
| 9 |
}
|
|
|
|
| 5 |
"eos_token_id": 2,
|
| 6 |
"forced_eos_token_id": 2,
|
| 7 |
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.33.2"
|
| 9 |
}
|
onnx/decoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7a31b04ee05ff5bd5e75a081894a510dd3892a8c3a7fa76e85f0e213cb63984
|
| 3 |
+
size 1017095876
|
onnx/decoder_model_merged.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87450b65c540809f2c735343abbd237be91bef62df161869664159945f51d0c1
|
| 3 |
+
size 1017578914
|
onnx/decoder_model_merged_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b46e2c42089740cbc5e54ffa62afe9c7abe57b951068a32fd1e1d2b6cec994cb
|
| 3 |
+
size 257436772
|
onnx/decoder_model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6639a3bc95d304c5d76e14880261a4d3fab7334255dbff1acddc5d0e33162454
|
| 3 |
+
size 256678971
|
onnx/decoder_with_past_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3243299478b01e4ef524c6ba1b6e9ea0dd70017658ba2973612f26ab088d2c2b
|
| 3 |
+
size 916254519
|
onnx/decoder_with_past_model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85065312f55524515c8cb091ec40f127aeef4bf1f45081f5cf29d730eea6f19c
|
| 3 |
+
size 231159887
|
onnx/encoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a00a8e345eb60f53b3318a4350498c954ba3fea321b5b9c6d89b28d6ac1d1e2
|
| 3 |
+
size 814946353
|
onnx/encoder_model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8073f86af8b1351a4fd888f5eb3dbe88c2bc710b52c00b8d649282030a69d56b
|
| 3 |
+
size 205101115
|
quantize_config.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"per_channel": true,
|
| 3 |
+
"reduce_range": true,
|
| 4 |
+
"per_model_config": {
|
| 5 |
+
"decoder_with_past_model": {
|
| 6 |
+
"op_types": [
|
| 7 |
+
"Cast",
|
| 8 |
+
"MatMul",
|
| 9 |
+
"Expand",
|
| 10 |
+
"Mul",
|
| 11 |
+
"Gather",
|
| 12 |
+
"ReduceMean",
|
| 13 |
+
"Add",
|
| 14 |
+
"Softmax",
|
| 15 |
+
"Shape",
|
| 16 |
+
"Equal",
|
| 17 |
+
"Range",
|
| 18 |
+
"Sqrt",
|
| 19 |
+
"Where",
|
| 20 |
+
"Sub",
|
| 21 |
+
"Reshape",
|
| 22 |
+
"Unsqueeze",
|
| 23 |
+
"Transpose",
|
| 24 |
+
"Constant",
|
| 25 |
+
"ConstantOfShape",
|
| 26 |
+
"Pow",
|
| 27 |
+
"Concat",
|
| 28 |
+
"Erf",
|
| 29 |
+
"Div"
|
| 30 |
+
],
|
| 31 |
+
"weight_type": "QInt8"
|
| 32 |
+
},
|
| 33 |
+
"decoder_model": {
|
| 34 |
+
"op_types": [
|
| 35 |
+
"Cast",
|
| 36 |
+
"MatMul",
|
| 37 |
+
"Expand",
|
| 38 |
+
"Mul",
|
| 39 |
+
"Gather",
|
| 40 |
+
"ReduceMean",
|
| 41 |
+
"Add",
|
| 42 |
+
"Softmax",
|
| 43 |
+
"Less",
|
| 44 |
+
"Shape",
|
| 45 |
+
"Equal",
|
| 46 |
+
"Range",
|
| 47 |
+
"Slice",
|
| 48 |
+
"Sqrt",
|
| 49 |
+
"Where",
|
| 50 |
+
"Sub",
|
| 51 |
+
"Reshape",
|
| 52 |
+
"Unsqueeze",
|
| 53 |
+
"Transpose",
|
| 54 |
+
"Constant",
|
| 55 |
+
"ConstantOfShape",
|
| 56 |
+
"Pow",
|
| 57 |
+
"Squeeze",
|
| 58 |
+
"Concat",
|
| 59 |
+
"Erf",
|
| 60 |
+
"Div"
|
| 61 |
+
],
|
| 62 |
+
"weight_type": "QInt8"
|
| 63 |
+
},
|
| 64 |
+
"encoder_model": {
|
| 65 |
+
"op_types": [
|
| 66 |
+
"Cast",
|
| 67 |
+
"MatMul",
|
| 68 |
+
"Expand",
|
| 69 |
+
"Mul",
|
| 70 |
+
"Gather",
|
| 71 |
+
"ReduceMean",
|
| 72 |
+
"Add",
|
| 73 |
+
"Softmax",
|
| 74 |
+
"Shape",
|
| 75 |
+
"Equal",
|
| 76 |
+
"Range",
|
| 77 |
+
"Sqrt",
|
| 78 |
+
"Where",
|
| 79 |
+
"Sub",
|
| 80 |
+
"Reshape",
|
| 81 |
+
"Unsqueeze",
|
| 82 |
+
"Transpose",
|
| 83 |
+
"Constant",
|
| 84 |
+
"ConstantOfShape",
|
| 85 |
+
"Pow",
|
| 86 |
+
"Concat",
|
| 87 |
+
"Erf",
|
| 88 |
+
"Div"
|
| 89 |
+
],
|
| 90 |
+
"weight_type": "QInt8"
|
| 91 |
+
},
|
| 92 |
+
"decoder_model_merged": {
|
| 93 |
+
"op_types": [
|
| 94 |
+
"Cast",
|
| 95 |
+
"MatMul",
|
| 96 |
+
"Expand",
|
| 97 |
+
"Mul",
|
| 98 |
+
"Gather",
|
| 99 |
+
"ReduceMean",
|
| 100 |
+
"Add",
|
| 101 |
+
"Softmax",
|
| 102 |
+
"Less",
|
| 103 |
+
"Shape",
|
| 104 |
+
"Equal",
|
| 105 |
+
"Range",
|
| 106 |
+
"Slice",
|
| 107 |
+
"Sqrt",
|
| 108 |
+
"Where",
|
| 109 |
+
"If",
|
| 110 |
+
"Sub",
|
| 111 |
+
"Reshape",
|
| 112 |
+
"Unsqueeze",
|
| 113 |
+
"Transpose",
|
| 114 |
+
"Constant",
|
| 115 |
+
"ConstantOfShape",
|
| 116 |
+
"Pow",
|
| 117 |
+
"Squeeze",
|
| 118 |
+
"Concat",
|
| 119 |
+
"Erf",
|
| 120 |
+
"Div"
|
| 121 |
+
],
|
| 122 |
+
"weight_type": "QInt8"
|
| 123 |
+
}
|
| 124 |
+
}
|
| 125 |
+
}
|