Init quantized project
Browse files- config.json +71 -0
- decoder_model_merged_quantized.onnx +3 -0
- decoder_model_quantized.onnx +3 -0
- decoder_with_past_model_quantized.onnx +3 -0
- encoder_model_quantized.onnx +3 -0
- merges.txt +0 -0
- ort_config.json +35 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +61 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gmarcFG/tech-keywords-extractor-onnx",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": ["BartForConditionalGeneration"],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classif_dropout": 0.1,
|
11 |
+
"classifier_dropout": 0.0,
|
12 |
+
"d_model": 1024,
|
13 |
+
"decoder_attention_heads": 16,
|
14 |
+
"decoder_ffn_dim": 4096,
|
15 |
+
"decoder_layerdrop": 0.0,
|
16 |
+
"decoder_layers": 12,
|
17 |
+
"decoder_start_token_id": 2,
|
18 |
+
"dropout": 0.1,
|
19 |
+
"early_stopping": true,
|
20 |
+
"encoder_attention_heads": 16,
|
21 |
+
"encoder_ffn_dim": 4096,
|
22 |
+
"encoder_layerdrop": 0.0,
|
23 |
+
"encoder_layers": 12,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"forced_bos_token_id": 0,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"gradient_checkpointing": false,
|
28 |
+
"id2label": {
|
29 |
+
"0": "LABEL_0",
|
30 |
+
"1": "LABEL_1",
|
31 |
+
"2": "LABEL_2"
|
32 |
+
},
|
33 |
+
"init_std": 0.02,
|
34 |
+
"is_encoder_decoder": true,
|
35 |
+
"label2id": {
|
36 |
+
"LABEL_0": 0,
|
37 |
+
"LABEL_1": 1,
|
38 |
+
"LABEL_2": 2
|
39 |
+
},
|
40 |
+
"max_position_embeddings": 1024,
|
41 |
+
"model_type": "bart",
|
42 |
+
"no_repeat_ngram_size": 3,
|
43 |
+
"normalize_before": false,
|
44 |
+
"num_beams": 4,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 1,
|
47 |
+
"scale_embedding": false,
|
48 |
+
"task_specific_params": {
|
49 |
+
"summarization": {
|
50 |
+
"length_penalty": 1.0,
|
51 |
+
"max_length": 128,
|
52 |
+
"min_length": 12,
|
53 |
+
"num_beams": 4
|
54 |
+
},
|
55 |
+
"summarization_cnn": {
|
56 |
+
"length_penalty": 2.0,
|
57 |
+
"max_length": 142,
|
58 |
+
"min_length": 56,
|
59 |
+
"num_beams": 4
|
60 |
+
},
|
61 |
+
"summarization_xsum": {
|
62 |
+
"length_penalty": 1.0,
|
63 |
+
"max_length": 62,
|
64 |
+
"min_length": 11,
|
65 |
+
"num_beams": 6
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"transformers_version": "4.39.3",
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 50265
|
71 |
+
}
|
decoder_model_merged_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02ccbadc73ddee1e74ea596ab7214c364ca3a650dec27d0168721816cf15ac3d
|
3 |
+
size 308444092
|
decoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bcde65a52062be82acba52dc5ae55cf11ce19922fabb1be49b4b9139d98875
|
3 |
+
size 307526044
|
decoder_with_past_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73729b428c1285e76af01dd75593e52adbbead33c034acc1a716b30907171f2
|
3 |
+
size 282113240
|
encoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ae5a5982a1ba8b8bd9210466e27923a141ebd5d263f7d02fa850747cc679bea
|
3 |
+
size 204631013
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ort_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"one_external_file": true,
|
3 |
+
"opset": null,
|
4 |
+
"optimization": {},
|
5 |
+
"optimum_version": "1.19.0",
|
6 |
+
"quantization": {
|
7 |
+
"activations_dtype": "QUInt8",
|
8 |
+
"activations_symmetric": false,
|
9 |
+
"format": "QOperator",
|
10 |
+
"is_static": false,
|
11 |
+
"mode": "IntegerOps",
|
12 |
+
"nodes_to_exclude": [],
|
13 |
+
"nodes_to_quantize": [],
|
14 |
+
"operators_to_quantize": [
|
15 |
+
"Conv",
|
16 |
+
"MatMul",
|
17 |
+
"Attention",
|
18 |
+
"LSTM",
|
19 |
+
"Gather",
|
20 |
+
"Transpose",
|
21 |
+
"EmbedLayerNormalization"
|
22 |
+
],
|
23 |
+
"per_channel": false,
|
24 |
+
"qdq_add_pair_to_weight": false,
|
25 |
+
"qdq_dedicated_pair": false,
|
26 |
+
"qdq_op_type_per_channel_support_to_axis": {
|
27 |
+
"MatMul": 1
|
28 |
+
},
|
29 |
+
"reduce_range": false,
|
30 |
+
"weights_dtype": "QInt8",
|
31 |
+
"weights_symmetric": true
|
32 |
+
},
|
33 |
+
"transformers_version": "4.39.3",
|
34 |
+
"use_external_data_format": false
|
35 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_length": 1024,
|
52 |
+
"model_max_length": 1024,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"stride": 0,
|
56 |
+
"tokenizer_class": "BartTokenizer",
|
57 |
+
"trim_offsets": true,
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "longest_first",
|
60 |
+
"unk_token": "<unk>"
|
61 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|