yujiepan commited on
Commit
6d5b6f3
1 Parent(s): bab79a6

Upload folder using huggingface_hub

Browse files
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/args.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_id": "neuralmagic/mpt-7b-gsm8k-pt",
3
+ "run_name": "w8a8-sparse70",
4
+ "quant_mode": "W8A8",
5
+ "ref_sparse_onnx": "neuralmagic/mpt-7b-gsm8k-pruned70-quant-ds",
6
+ "force_run": true
7
+ }
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/compressed_graph.dot ADDED
The diff for this file is too large to render. See raw diff
 
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmagic/mpt-7b-gsm8k-pt",
3
+ "architectures": [
4
+ "MPTForCausalLM"
5
+ ],
6
+ "attn_config": {
7
+ "model_type": ""
8
+ },
9
+ "auto_map": {
10
+ "AutoConfig": "neuralmagic/mpt-7b-gsm8k-pt--configuration_mpt.MPTConfig",
11
+ "AutoModelForCausalLM": "neuralmagic/mpt-7b-gsm8k-pt--modeling_mpt.MPTForCausalLM"
12
+ },
13
+ "d_model": 4096,
14
+ "emb_pdrop": 0,
15
+ "embedding_fraction": 1.0,
16
+ "expansion_ratio": 4,
17
+ "init_config": {
18
+ "emb_init_std": null,
19
+ "emb_init_uniform_lim": null,
20
+ "fan_mode": "fan_in",
21
+ "init_div_is_residual": true,
22
+ "init_gain": 0,
23
+ "init_nonlinearity": "relu",
24
+ "init_std": 0.02,
25
+ "name": "kaiming_normal_",
26
+ "verbose": 0
27
+ },
28
+ "init_device": "cpu",
29
+ "initializer_range": 0.02,
30
+ "layer_norm_epsilon": 1e-05,
31
+ "learned_pos_emb": true,
32
+ "logit_scale": null,
33
+ "max_seq_len": 2048,
34
+ "model_type": "mpt",
35
+ "n_heads": 32,
36
+ "n_layers": 32,
37
+ "no_bias": true,
38
+ "norm_type": "low_precision_layernorm",
39
+ "resid_pdrop": 0,
40
+ "tie_weights": false,
41
+ "tie_word_embeddings": false,
42
+ "tokenizer_name": "EleutherAI/gpt-neox-20b",
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.34.1",
45
+ "use_cache": true,
46
+ "verbose": 0,
47
+ "vocab_size": 50432
48
+ }
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/log.log ADDED
The diff for this file is too large to render. See raw diff
 
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/openvino_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "compression": {
3
+ "algorithm": "quantization",
4
+ "export_to_onnx_standard_ops": false,
5
+ "ignored_scopes": [
6
+ "{re}.*layer_norm_.*"
7
+ ],
8
+ "initializer": {
9
+ "batchnorm_adaptation": {
10
+ "num_bn_adaptation_samples": 0
11
+ },
12
+ "range": {
13
+ "num_init_samples": 4,
14
+ "type": "mean_min_max"
15
+ }
16
+ },
17
+ "overflow_fix": "disable",
18
+ "preset": "performance",
19
+ "scope_overrides": {
20
+ "activations": {
21
+ "{re}.*matmul_0": {
22
+ "mode": "symmetric"
23
+ }
24
+ }
25
+ }
26
+ },
27
+ "input_info": [
28
+ {
29
+ "keyword": "input_ids",
30
+ "sample_size": [
31
+ 1,
32
+ 8
33
+ ],
34
+ "type": "long"
35
+ },
36
+ {
37
+ "keyword": "attention_mask",
38
+ "sample_size": [
39
+ 1,
40
+ 8
41
+ ],
42
+ "type": "long"
43
+ }
44
+ ],
45
+ "log_dir": "models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70",
46
+ "optimum_version": "1.14.1",
47
+ "save_onnx_model": false,
48
+ "target_device": "CPU",
49
+ "transformers_version": "4.34.1"
50
+ }
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c12c5bce4f4fa6f2a6de4ba2dce71472e076cdc9eb9ea6936772777486d3c
3
+ size 6655271181
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/original_graph.dot ADDED
The diff for this file is too large to render. See raw diff
 
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/ov_weights_type.md ADDED
@@ -0,0 +1,328 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | | name | shape | type | sparsity |
2
+ |----:|:----------------------------------------------------------------|:-------------|:------------------|-----------:|
3
+ | 0 | Constant_172536 | [50432,4096] | <Type: 'int8_t'> | 0.0132285 |
4
+ | 1 | Constant_172538 | [50432,1] | <Type: 'float32'> | 0 |
5
+ | 2 | Constant_165621 | [1,1,4096] | <Type: 'float32'> | 0 |
6
+ | 3 | Constant_172540 | [12288,4096] | <Type: 'int8_t'> | 0.741039 |
7
+ | 4 | Constant_172542 | [12288,1] | <Type: 'float32'> | 0 |
8
+ | 5 | __module.model.transformer.blocks.0.attn/aten::slice/Slice_2965 | [32,1,2048] | <Type: 'float32'> | 0 |
9
+ | 6 | Constant_172544 | [4096,4096] | <Type: 'int8_t'> | 0.700155 |
10
+ | 7 | Constant_172546 | [4096,1] | <Type: 'float32'> | 0 |
11
+ | 8 | Constant_165659 | [1,1,4096] | <Type: 'float32'> | 0 |
12
+ | 9 | Constant_172548 | [16384,4096] | <Type: 'int8_t'> | 0.700153 |
13
+ | 10 | Constant_172550 | [16384,1] | <Type: 'float32'> | 0 |
14
+ | 11 | Constant_172552 | [4096,16384] | <Type: 'int8_t'> | 0.700551 |
15
+ | 12 | Constant_172554 | [4096,1] | <Type: 'float32'> | 0 |
16
+ | 13 | Constant_165676 | [1,1,4096] | <Type: 'float32'> | 0 |
17
+ | 14 | Constant_172556 | [12288,4096] | <Type: 'int8_t'> | 0.700357 |
18
+ | 15 | Constant_172558 | [12288,1] | <Type: 'float32'> | 0 |
19
+ | 16 | Constant_172560 | [4096,4096] | <Type: 'int8_t'> | 0.701611 |
20
+ | 17 | Constant_172562 | [4096,1] | <Type: 'float32'> | 0 |
21
+ | 18 | Constant_165714 | [1,1,4096] | <Type: 'float32'> | 0 |
22
+ | 19 | Constant_172564 | [16384,4096] | <Type: 'int8_t'> | 0.700289 |
23
+ | 20 | Constant_172566 | [16384,1] | <Type: 'float32'> | 0 |
24
+ | 21 | Constant_172568 | [4096,16384] | <Type: 'int8_t'> | 0.700118 |
25
+ | 22 | Constant_172570 | [4096,1] | <Type: 'float32'> | 0 |
26
+ | 23 | Constant_165731 | [1,1,4096] | <Type: 'float32'> | 0 |
27
+ | 24 | Constant_172572 | [12288,4096] | <Type: 'int8_t'> | 0.700334 |
28
+ | 25 | Constant_172574 | [12288,1] | <Type: 'float32'> | 0 |
29
+ | 26 | Constant_172576 | [4096,4096] | <Type: 'int8_t'> | 0.701027 |
30
+ | 27 | Constant_172578 | [4096,1] | <Type: 'float32'> | 0 |
31
+ | 28 | Constant_165769 | [1,1,4096] | <Type: 'float32'> | 0 |
32
+ | 29 | Constant_172580 | [16384,4096] | <Type: 'int8_t'> | 0.700194 |
33
+ | 30 | Constant_172582 | [16384,1] | <Type: 'float32'> | 0 |
34
+ | 31 | Constant_172584 | [4096,16384] | <Type: 'int8_t'> | 0.700151 |
35
+ | 32 | Constant_172586 | [4096,1] | <Type: 'float32'> | 0 |
36
+ | 33 | Constant_165786 | [1,1,4096] | <Type: 'float32'> | 0 |
37
+ | 34 | Constant_172588 | [12288,4096] | <Type: 'int8_t'> | 0.700264 |
38
+ | 35 | Constant_172590 | [12288,1] | <Type: 'float32'> | 0 |
39
+ | 36 | Constant_172592 | [4096,4096] | <Type: 'int8_t'> | 0.701121 |
40
+ | 37 | Constant_172594 | [4096,1] | <Type: 'float32'> | 0 |
41
+ | 38 | Constant_165824 | [1,1,4096] | <Type: 'float32'> | 0 |
42
+ | 39 | Constant_172596 | [16384,4096] | <Type: 'int8_t'> | 0.700187 |
43
+ | 40 | Constant_172598 | [16384,1] | <Type: 'float32'> | 0 |
44
+ | 41 | Constant_172600 | [4096,16384] | <Type: 'int8_t'> | 0.700264 |
45
+ | 42 | Constant_172602 | [4096,1] | <Type: 'float32'> | 0 |
46
+ | 43 | Constant_165841 | [1,1,4096] | <Type: 'float32'> | 0 |
47
+ | 44 | Constant_172604 | [12288,4096] | <Type: 'int8_t'> | 0.700241 |
48
+ | 45 | Constant_172606 | [12288,1] | <Type: 'float32'> | 0 |
49
+ | 46 | Constant_172608 | [4096,4096] | <Type: 'int8_t'> | 0.701052 |
50
+ | 47 | Constant_172610 | [4096,1] | <Type: 'float32'> | 0 |
51
+ | 48 | Constant_165879 | [1,1,4096] | <Type: 'float32'> | 0 |
52
+ | 49 | Constant_172612 | [16384,4096] | <Type: 'int8_t'> | 0.700179 |
53
+ | 50 | Constant_172614 | [16384,1] | <Type: 'float32'> | 0 |
54
+ | 51 | Constant_172616 | [4096,16384] | <Type: 'int8_t'> | 0.700188 |
55
+ | 52 | Constant_172618 | [4096,1] | <Type: 'float32'> | 0 |
56
+ | 53 | Constant_165896 | [1,1,4096] | <Type: 'float32'> | 0 |
57
+ | 54 | Constant_172620 | [12288,4096] | <Type: 'int8_t'> | 0.70021 |
58
+ | 55 | Constant_172622 | [12288,1] | <Type: 'float32'> | 0 |
59
+ | 56 | Constant_172624 | [4096,4096] | <Type: 'int8_t'> | 0.700989 |
60
+ | 57 | Constant_172626 | [4096,1] | <Type: 'float32'> | 0 |
61
+ | 58 | Constant_165934 | [1,1,4096] | <Type: 'float32'> | 0 |
62
+ | 59 | Constant_172628 | [16384,4096] | <Type: 'int8_t'> | 0.70017 |
63
+ | 60 | Constant_172630 | [16384,1] | <Type: 'float32'> | 0 |
64
+ | 61 | Constant_172632 | [4096,16384] | <Type: 'int8_t'> | 0.700191 |
65
+ | 62 | Constant_172634 | [4096,1] | <Type: 'float32'> | 0 |
66
+ | 63 | Constant_165951 | [1,1,4096] | <Type: 'float32'> | 0 |
67
+ | 64 | Constant_172636 | [12288,4096] | <Type: 'int8_t'> | 0.700195 |
68
+ | 65 | Constant_172638 | [12288,1] | <Type: 'float32'> | 0 |
69
+ | 66 | Constant_172640 | [4096,4096] | <Type: 'int8_t'> | 0.705793 |
70
+ | 67 | Constant_172642 | [4096,1] | <Type: 'float32'> | 0 |
71
+ | 68 | Constant_165989 | [1,1,4096] | <Type: 'float32'> | 0 |
72
+ | 69 | Constant_172644 | [16384,4096] | <Type: 'int8_t'> | 0.700168 |
73
+ | 70 | Constant_172646 | [16384,1] | <Type: 'float32'> | 0 |
74
+ | 71 | Constant_172648 | [4096,16384] | <Type: 'int8_t'> | 0.700159 |
75
+ | 72 | Constant_172650 | [4096,1] | <Type: 'float32'> | 0 |
76
+ | 73 | Constant_166006 | [1,1,4096] | <Type: 'float32'> | 0 |
77
+ | 74 | Constant_172652 | [12288,4096] | <Type: 'int8_t'> | 0.700183 |
78
+ | 75 | Constant_172654 | [12288,1] | <Type: 'float32'> | 0 |
79
+ | 76 | Constant_172656 | [4096,4096] | <Type: 'int8_t'> | 0.700801 |
80
+ | 77 | Constant_172658 | [4096,1] | <Type: 'float32'> | 0 |
81
+ | 78 | Constant_166044 | [1,1,4096] | <Type: 'float32'> | 0 |
82
+ | 79 | Constant_172660 | [16384,4096] | <Type: 'int8_t'> | 0.700179 |
83
+ | 80 | Constant_172662 | [16384,1] | <Type: 'float32'> | 0 |
84
+ | 81 | Constant_172664 | [4096,16384] | <Type: 'int8_t'> | 0.70027 |
85
+ | 82 | Constant_172666 | [4096,1] | <Type: 'float32'> | 0 |
86
+ | 83 | Constant_166061 | [1,1,4096] | <Type: 'float32'> | 0 |
87
+ | 84 | Constant_172668 | [12288,4096] | <Type: 'int8_t'> | 0.700177 |
88
+ | 85 | Constant_172670 | [12288,1] | <Type: 'float32'> | 0 |
89
+ | 86 | Constant_172672 | [4096,4096] | <Type: 'int8_t'> | 0.700593 |
90
+ | 87 | Constant_172674 | [4096,1] | <Type: 'float32'> | 0 |
91
+ | 88 | Constant_166099 | [1,1,4096] | <Type: 'float32'> | 0 |
92
+ | 89 | Constant_172676 | [16384,4096] | <Type: 'int8_t'> | 0.700156 |
93
+ | 90 | Constant_172678 | [16384,1] | <Type: 'float32'> | 0 |
94
+ | 91 | Constant_172680 | [4096,16384] | <Type: 'int8_t'> | 0.700139 |
95
+ | 92 | Constant_172682 | [4096,1] | <Type: 'float32'> | 0 |
96
+ | 93 | Constant_166116 | [1,1,4096] | <Type: 'float32'> | 0 |
97
+ | 94 | Constant_172684 | [12288,4096] | <Type: 'int8_t'> | 0.700173 |
98
+ | 95 | Constant_172686 | [12288,1] | <Type: 'float32'> | 0 |
99
+ | 96 | Constant_172688 | [4096,4096] | <Type: 'int8_t'> | 0.700544 |
100
+ | 97 | Constant_172690 | [4096,1] | <Type: 'float32'> | 0 |
101
+ | 98 | Constant_166154 | [1,1,4096] | <Type: 'float32'> | 0 |
102
+ | 99 | Constant_172692 | [16384,4096] | <Type: 'int8_t'> | 0.700152 |
103
+ | 100 | Constant_172694 | [16384,1] | <Type: 'float32'> | 0 |
104
+ | 101 | Constant_172696 | [4096,16384] | <Type: 'int8_t'> | 0.700401 |
105
+ | 102 | Constant_172698 | [4096,1] | <Type: 'float32'> | 0 |
106
+ | 103 | Constant_166171 | [1,1,4096] | <Type: 'float32'> | 0 |
107
+ | 104 | Constant_172700 | [12288,4096] | <Type: 'int8_t'> | 0.700158 |
108
+ | 105 | Constant_172702 | [12288,1] | <Type: 'float32'> | 0 |
109
+ | 106 | Constant_172704 | [4096,4096] | <Type: 'int8_t'> | 0.700559 |
110
+ | 107 | Constant_172706 | [4096,1] | <Type: 'float32'> | 0 |
111
+ | 108 | Constant_166209 | [1,1,4096] | <Type: 'float32'> | 0 |
112
+ | 109 | Constant_172708 | [16384,4096] | <Type: 'int8_t'> | 0.700153 |
113
+ | 110 | Constant_172710 | [16384,1] | <Type: 'float32'> | 0 |
114
+ | 111 | Constant_172712 | [4096,16384] | <Type: 'int8_t'> | 0.700149 |
115
+ | 112 | Constant_172714 | [4096,1] | <Type: 'float32'> | 0 |
116
+ | 113 | Constant_166226 | [1,1,4096] | <Type: 'float32'> | 0 |
117
+ | 114 | Constant_172716 | [12288,4096] | <Type: 'int8_t'> | 0.70015 |
118
+ | 115 | Constant_172718 | [12288,1] | <Type: 'float32'> | 0 |
119
+ | 116 | Constant_172720 | [4096,4096] | <Type: 'int8_t'> | 0.700426 |
120
+ | 117 | Constant_172722 | [4096,1] | <Type: 'float32'> | 0 |
121
+ | 118 | Constant_166264 | [1,1,4096] | <Type: 'float32'> | 0 |
122
+ | 119 | Constant_172724 | [16384,4096] | <Type: 'int8_t'> | 0.700154 |
123
+ | 120 | Constant_172726 | [16384,1] | <Type: 'float32'> | 0 |
124
+ | 121 | Constant_172728 | [4096,16384] | <Type: 'int8_t'> | 0.700191 |
125
+ | 122 | Constant_172730 | [4096,1] | <Type: 'float32'> | 0 |
126
+ | 123 | Constant_166281 | [1,1,4096] | <Type: 'float32'> | 0 |
127
+ | 124 | Constant_172732 | [12288,4096] | <Type: 'int8_t'> | 0.700154 |
128
+ | 125 | Constant_172734 | [12288,1] | <Type: 'float32'> | 0 |
129
+ | 126 | Constant_172736 | [4096,4096] | <Type: 'int8_t'> | 0.700569 |
130
+ | 127 | Constant_172738 | [4096,1] | <Type: 'float32'> | 0 |
131
+ | 128 | Constant_166319 | [1,1,4096] | <Type: 'float32'> | 0 |
132
+ | 129 | Constant_172740 | [16384,4096] | <Type: 'int8_t'> | 0.700148 |
133
+ | 130 | Constant_172742 | [16384,1] | <Type: 'float32'> | 0 |
134
+ | 131 | Constant_172744 | [4096,16384] | <Type: 'int8_t'> | 0.700142 |
135
+ | 132 | Constant_172746 | [4096,1] | <Type: 'float32'> | 0 |
136
+ | 133 | Constant_166336 | [1,1,4096] | <Type: 'float32'> | 0 |
137
+ | 134 | Constant_172748 | [12288,4096] | <Type: 'int8_t'> | 0.700148 |
138
+ | 135 | Constant_172750 | [12288,1] | <Type: 'float32'> | 0 |
139
+ | 136 | Constant_172752 | [4096,4096] | <Type: 'int8_t'> | 0.700566 |
140
+ | 137 | Constant_172754 | [4096,1] | <Type: 'float32'> | 0 |
141
+ | 138 | Constant_166374 | [1,1,4096] | <Type: 'float32'> | 0 |
142
+ | 139 | Constant_172756 | [16384,4096] | <Type: 'int8_t'> | 0.700148 |
143
+ | 140 | Constant_172758 | [16384,1] | <Type: 'float32'> | 0 |
144
+ | 141 | Constant_172760 | [4096,16384] | <Type: 'int8_t'> | 0.700171 |
145
+ | 142 | Constant_172762 | [4096,1] | <Type: 'float32'> | 0 |
146
+ | 143 | Constant_166391 | [1,1,4096] | <Type: 'float32'> | 0 |
147
+ | 144 | Constant_172764 | [12288,4096] | <Type: 'int8_t'> | 0.700143 |
148
+ | 145 | Constant_172766 | [12288,1] | <Type: 'float32'> | 0 |
149
+ | 146 | Constant_172768 | [4096,4096] | <Type: 'int8_t'> | 0.700591 |
150
+ | 147 | Constant_172770 | [4096,1] | <Type: 'float32'> | 0 |
151
+ | 148 | Constant_166429 | [1,1,4096] | <Type: 'float32'> | 0 |
152
+ | 149 | Constant_172772 | [16384,4096] | <Type: 'int8_t'> | 0.700145 |
153
+ | 150 | Constant_172774 | [16384,1] | <Type: 'float32'> | 0 |
154
+ | 151 | Constant_172776 | [4096,16384] | <Type: 'int8_t'> | 0.700161 |
155
+ | 152 | Constant_172778 | [4096,1] | <Type: 'float32'> | 0 |
156
+ | 153 | Constant_166446 | [1,1,4096] | <Type: 'float32'> | 0 |
157
+ | 154 | Constant_172780 | [12288,4096] | <Type: 'int8_t'> | 0.700138 |
158
+ | 155 | Constant_172782 | [12288,1] | <Type: 'float32'> | 0 |
159
+ | 156 | Constant_172784 | [4096,4096] | <Type: 'int8_t'> | 0.700433 |
160
+ | 157 | Constant_172786 | [4096,1] | <Type: 'float32'> | 0 |
161
+ | 158 | Constant_166484 | [1,1,4096] | <Type: 'float32'> | 0 |
162
+ | 159 | Constant_172788 | [16384,4096] | <Type: 'int8_t'> | 0.700144 |
163
+ | 160 | Constant_172790 | [16384,1] | <Type: 'float32'> | 0 |
164
+ | 161 | Constant_172792 | [4096,16384] | <Type: 'int8_t'> | 0.70022 |
165
+ | 162 | Constant_172794 | [4096,1] | <Type: 'float32'> | 0 |
166
+ | 163 | Constant_166501 | [1,1,4096] | <Type: 'float32'> | 0 |
167
+ | 164 | Constant_172796 | [12288,4096] | <Type: 'int8_t'> | 0.700138 |
168
+ | 165 | Constant_172798 | [12288,1] | <Type: 'float32'> | 0 |
169
+ | 166 | Constant_172800 | [4096,4096] | <Type: 'int8_t'> | 0.700493 |
170
+ | 167 | Constant_172802 | [4096,1] | <Type: 'float32'> | 0 |
171
+ | 168 | Constant_166539 | [1,1,4096] | <Type: 'float32'> | 0 |
172
+ | 169 | Constant_172804 | [16384,4096] | <Type: 'int8_t'> | 0.700137 |
173
+ | 170 | Constant_172806 | [16384,1] | <Type: 'float32'> | 0 |
174
+ | 171 | Constant_172808 | [4096,16384] | <Type: 'int8_t'> | 0.700188 |
175
+ | 172 | Constant_172810 | [4096,1] | <Type: 'float32'> | 0 |
176
+ | 173 | Constant_166556 | [1,1,4096] | <Type: 'float32'> | 0 |
177
+ | 174 | Constant_172812 | [12288,4096] | <Type: 'int8_t'> | 0.70014 |
178
+ | 175 | Constant_172814 | [12288,1] | <Type: 'float32'> | 0 |
179
+ | 176 | Constant_172816 | [4096,4096] | <Type: 'int8_t'> | 0.700479 |
180
+ | 177 | Constant_172818 | [4096,1] | <Type: 'float32'> | 0 |
181
+ | 178 | Constant_166594 | [1,1,4096] | <Type: 'float32'> | 0 |
182
+ | 179 | Constant_172820 | [16384,4096] | <Type: 'int8_t'> | 0.700134 |
183
+ | 180 | Constant_172822 | [16384,1] | <Type: 'float32'> | 0 |
184
+ | 181 | Constant_172824 | [4096,16384] | <Type: 'int8_t'> | 0.700158 |
185
+ | 182 | Constant_172826 | [4096,1] | <Type: 'float32'> | 0 |
186
+ | 183 | Constant_166611 | [1,1,4096] | <Type: 'float32'> | 0 |
187
+ | 184 | Constant_172828 | [12288,4096] | <Type: 'int8_t'> | 0.700129 |
188
+ | 185 | Constant_172830 | [12288,1] | <Type: 'float32'> | 0 |
189
+ | 186 | Constant_172832 | [4096,4096] | <Type: 'int8_t'> | 0.700606 |
190
+ | 187 | Constant_172834 | [4096,1] | <Type: 'float32'> | 0 |
191
+ | 188 | Constant_166649 | [1,1,4096] | <Type: 'float32'> | 0 |
192
+ | 189 | Constant_172836 | [16384,4096] | <Type: 'int8_t'> | 0.700133 |
193
+ | 190 | Constant_172838 | [16384,1] | <Type: 'float32'> | 0 |
194
+ | 191 | Constant_172840 | [4096,16384] | <Type: 'int8_t'> | 0.700149 |
195
+ | 192 | Constant_172842 | [4096,1] | <Type: 'float32'> | 0 |
196
+ | 193 | Constant_166666 | [1,1,4096] | <Type: 'float32'> | 0 |
197
+ | 194 | Constant_172844 | [12288,4096] | <Type: 'int8_t'> | 0.700137 |
198
+ | 195 | Constant_172846 | [12288,1] | <Type: 'float32'> | 0 |
199
+ | 196 | Constant_172848 | [4096,4096] | <Type: 'int8_t'> | 0.700495 |
200
+ | 197 | Constant_172850 | [4096,1] | <Type: 'float32'> | 0 |
201
+ | 198 | Constant_166704 | [1,1,4096] | <Type: 'float32'> | 0 |
202
+ | 199 | Constant_172852 | [16384,4096] | <Type: 'int8_t'> | 0.700151 |
203
+ | 200 | Constant_172854 | [16384,1] | <Type: 'float32'> | 0 |
204
+ | 201 | Constant_172856 | [4096,16384] | <Type: 'int8_t'> | 0.700191 |
205
+ | 202 | Constant_172858 | [4096,1] | <Type: 'float32'> | 0 |
206
+ | 203 | Constant_166721 | [1,1,4096] | <Type: 'float32'> | 0 |
207
+ | 204 | Constant_172860 | [12288,4096] | <Type: 'int8_t'> | 0.700137 |
208
+ | 205 | Constant_172862 | [12288,1] | <Type: 'float32'> | 0 |
209
+ | 206 | Constant_172864 | [4096,4096] | <Type: 'int8_t'> | 0.700711 |
210
+ | 207 | Constant_172866 | [4096,1] | <Type: 'float32'> | 0 |
211
+ | 208 | Constant_166759 | [1,1,4096] | <Type: 'float32'> | 0 |
212
+ | 209 | Constant_172868 | [16384,4096] | <Type: 'int8_t'> | 0.700142 |
213
+ | 210 | Constant_172870 | [16384,1] | <Type: 'float32'> | 0 |
214
+ | 211 | Constant_172872 | [4096,16384] | <Type: 'int8_t'> | 0.700121 |
215
+ | 212 | Constant_172874 | [4096,1] | <Type: 'float32'> | 0 |
216
+ | 213 | Constant_166776 | [1,1,4096] | <Type: 'float32'> | 0 |
217
+ | 214 | Constant_172876 | [12288,4096] | <Type: 'int8_t'> | 0.700136 |
218
+ | 215 | Constant_172878 | [12288,1] | <Type: 'float32'> | 0 |
219
+ | 216 | Constant_172880 | [4096,4096] | <Type: 'int8_t'> | 0.7006 |
220
+ | 217 | Constant_172882 | [4096,1] | <Type: 'float32'> | 0 |
221
+ | 218 | Constant_166814 | [1,1,4096] | <Type: 'float32'> | 0 |
222
+ | 219 | Constant_172884 | [16384,4096] | <Type: 'int8_t'> | 0.70013 |
223
+ | 220 | Constant_172886 | [16384,1] | <Type: 'float32'> | 0 |
224
+ | 221 | Constant_172888 | [4096,16384] | <Type: 'int8_t'> | 0.700133 |
225
+ | 222 | Constant_172890 | [4096,1] | <Type: 'float32'> | 0 |
226
+ | 223 | Constant_166831 | [1,1,4096] | <Type: 'float32'> | 0 |
227
+ | 224 | Constant_172892 | [12288,4096] | <Type: 'int8_t'> | 0.700133 |
228
+ | 225 | Constant_172894 | [12288,1] | <Type: 'float32'> | 0 |
229
+ | 226 | Constant_172896 | [4096,4096] | <Type: 'int8_t'> | 0.700553 |
230
+ | 227 | Constant_172898 | [4096,1] | <Type: 'float32'> | 0 |
231
+ | 228 | Constant_166869 | [1,1,4096] | <Type: 'float32'> | 0 |
232
+ | 229 | Constant_172900 | [16384,4096] | <Type: 'int8_t'> | 0.700133 |
233
+ | 230 | Constant_172902 | [16384,1] | <Type: 'float32'> | 0 |
234
+ | 231 | Constant_172904 | [4096,16384] | <Type: 'int8_t'> | 0.700228 |
235
+ | 232 | Constant_172906 | [4096,1] | <Type: 'float32'> | 0 |
236
+ | 233 | Constant_166886 | [1,1,4096] | <Type: 'float32'> | 0 |
237
+ | 234 | Constant_172908 | [12288,4096] | <Type: 'int8_t'> | 0.700142 |
238
+ | 235 | Constant_172910 | [12288,1] | <Type: 'float32'> | 0 |
239
+ | 236 | Constant_172912 | [4096,4096] | <Type: 'int8_t'> | 0.700653 |
240
+ | 237 | Constant_172914 | [4096,1] | <Type: 'float32'> | 0 |
241
+ | 238 | Constant_166924 | [1,1,4096] | <Type: 'float32'> | 0 |
242
+ | 239 | Constant_172916 | [16384,4096] | <Type: 'int8_t'> | 0.700127 |
243
+ | 240 | Constant_172918 | [16384,1] | <Type: 'float32'> | 0 |
244
+ | 241 | Constant_172920 | [4096,16384] | <Type: 'int8_t'> | 0.700153 |
245
+ | 242 | Constant_172922 | [4096,1] | <Type: 'float32'> | 0 |
246
+ | 243 | Constant_166941 | [1,1,4096] | <Type: 'float32'> | 0 |
247
+ | 244 | Constant_172924 | [12288,4096] | <Type: 'int8_t'> | 0.700134 |
248
+ | 245 | Constant_172926 | [12288,1] | <Type: 'float32'> | 0 |
249
+ | 246 | Constant_172928 | [4096,4096] | <Type: 'int8_t'> | 0.700658 |
250
+ | 247 | Constant_172930 | [4096,1] | <Type: 'float32'> | 0 |
251
+ | 248 | Constant_166979 | [1,1,4096] | <Type: 'float32'> | 0 |
252
+ | 249 | Constant_172932 | [16384,4096] | <Type: 'int8_t'> | 0.700127 |
253
+ | 250 | Constant_172934 | [16384,1] | <Type: 'float32'> | 0 |
254
+ | 251 | Constant_172936 | [4096,16384] | <Type: 'int8_t'> | 0.700131 |
255
+ | 252 | Constant_172938 | [4096,1] | <Type: 'float32'> | 0 |
256
+ | 253 | Constant_166996 | [1,1,4096] | <Type: 'float32'> | 0 |
257
+ | 254 | Constant_172940 | [12288,4096] | <Type: 'int8_t'> | 0.700133 |
258
+ | 255 | Constant_172942 | [12288,1] | <Type: 'float32'> | 0 |
259
+ | 256 | Constant_172944 | [4096,4096] | <Type: 'int8_t'> | 0.701035 |
260
+ | 257 | Constant_172946 | [4096,1] | <Type: 'float32'> | 0 |
261
+ | 258 | Constant_167034 | [1,1,4096] | <Type: 'float32'> | 0 |
262
+ | 259 | Constant_172948 | [16384,4096] | <Type: 'int8_t'> | 0.70012 |
263
+ | 260 | Constant_172950 | [16384,1] | <Type: 'float32'> | 0 |
264
+ | 261 | Constant_172952 | [4096,16384] | <Type: 'int8_t'> | 0.700101 |
265
+ | 262 | Constant_172954 | [4096,1] | <Type: 'float32'> | 0 |
266
+ | 263 | Constant_167051 | [1,1,4096] | <Type: 'float32'> | 0 |
267
+ | 264 | Constant_172956 | [12288,4096] | <Type: 'int8_t'> | 0.700144 |
268
+ | 265 | Constant_172958 | [12288,1] | <Type: 'float32'> | 0 |
269
+ | 266 | Constant_172960 | [4096,4096] | <Type: 'int8_t'> | 0.700789 |
270
+ | 267 | Constant_172962 | [4096,1] | <Type: 'float32'> | 0 |
271
+ | 268 | Constant_167089 | [1,1,4096] | <Type: 'float32'> | 0 |
272
+ | 269 | Constant_172964 | [16384,4096] | <Type: 'int8_t'> | 0.700119 |
273
+ | 270 | Constant_172966 | [16384,1] | <Type: 'float32'> | 0 |
274
+ | 271 | Constant_172968 | [4096,16384] | <Type: 'int8_t'> | 0.700095 |
275
+ | 272 | Constant_172970 | [4096,1] | <Type: 'float32'> | 0 |
276
+ | 273 | Constant_167106 | [1,1,4096] | <Type: 'float32'> | 0 |
277
+ | 274 | Constant_172972 | [12288,4096] | <Type: 'int8_t'> | 0.700135 |
278
+ | 275 | Constant_172974 | [12288,1] | <Type: 'float32'> | 0 |
279
+ | 276 | Constant_172976 | [4096,4096] | <Type: 'int8_t'> | 0.700611 |
280
+ | 277 | Constant_172978 | [4096,1] | <Type: 'float32'> | 0 |
281
+ | 278 | Constant_167144 | [1,1,4096] | <Type: 'float32'> | 0 |
282
+ | 279 | Constant_172980 | [16384,4096] | <Type: 'int8_t'> | 0.700116 |
283
+ | 280 | Constant_172982 | [16384,1] | <Type: 'float32'> | 0 |
284
+ | 281 | Constant_172984 | [4096,16384] | <Type: 'int8_t'> | 0.700122 |
285
+ | 282 | Constant_172986 | [4096,1] | <Type: 'float32'> | 0 |
286
+ | 283 | Constant_167161 | [1,1,4096] | <Type: 'float32'> | 0 |
287
+ | 284 | Constant_172988 | [12288,4096] | <Type: 'int8_t'> | 0.700128 |
288
+ | 285 | Constant_172990 | [12288,1] | <Type: 'float32'> | 0 |
289
+ | 286 | Constant_172992 | [4096,4096] | <Type: 'int8_t'> | 0.700809 |
290
+ | 287 | Constant_172994 | [4096,1] | <Type: 'float32'> | 0 |
291
+ | 288 | Constant_167199 | [1,1,4096] | <Type: 'float32'> | 0 |
292
+ | 289 | Constant_172996 | [16384,4096] | <Type: 'int8_t'> | 0.700118 |
293
+ | 290 | Constant_172998 | [16384,1] | <Type: 'float32'> | 0 |
294
+ | 291 | Constant_173000 | [4096,16384] | <Type: 'int8_t'> | 0.700141 |
295
+ | 292 | Constant_173002 | [4096,1] | <Type: 'float32'> | 0 |
296
+ | 293 | Constant_167216 | [1,1,4096] | <Type: 'float32'> | 0 |
297
+ | 294 | Constant_173004 | [12288,4096] | <Type: 'int8_t'> | 0.700134 |
298
+ | 295 | Constant_173006 | [12288,1] | <Type: 'float32'> | 0 |
299
+ | 296 | Constant_173008 | [4096,4096] | <Type: 'int8_t'> | 0.700483 |
300
+ | 297 | Constant_173010 | [4096,1] | <Type: 'float32'> | 0 |
301
+ | 298 | Constant_167254 | [1,1,4096] | <Type: 'float32'> | 0 |
302
+ | 299 | Constant_173012 | [16384,4096] | <Type: 'int8_t'> | 0.70012 |
303
+ | 300 | Constant_173014 | [16384,1] | <Type: 'float32'> | 0 |
304
+ | 301 | Constant_173016 | [4096,16384] | <Type: 'int8_t'> | 0.700152 |
305
+ | 302 | Constant_173018 | [4096,1] | <Type: 'float32'> | 0 |
306
+ | 303 | Constant_167271 | [1,1,4096] | <Type: 'float32'> | 0 |
307
+ | 304 | Constant_173020 | [12288,4096] | <Type: 'int8_t'> | 0.700134 |
308
+ | 305 | Constant_173022 | [12288,1] | <Type: 'float32'> | 0 |
309
+ | 306 | Constant_173024 | [4096,4096] | <Type: 'int8_t'> | 0.700556 |
310
+ | 307 | Constant_173026 | [4096,1] | <Type: 'float32'> | 0 |
311
+ | 308 | Constant_167309 | [1,1,4096] | <Type: 'float32'> | 0 |
312
+ | 309 | Constant_173028 | [16384,4096] | <Type: 'int8_t'> | 0.700115 |
313
+ | 310 | Constant_173030 | [16384,1] | <Type: 'float32'> | 0 |
314
+ | 311 | Constant_173032 | [4096,16384] | <Type: 'int8_t'> | 0.700185 |
315
+ | 312 | Constant_173034 | [4096,1] | <Type: 'float32'> | 0 |
316
+ | 313 | Constant_167326 | [1,1,4096] | <Type: 'float32'> | 0 |
317
+ | 314 | Constant_173036 | [12288,4096] | <Type: 'int8_t'> | 0.700115 |
318
+ | 315 | Constant_173038 | [12288,1] | <Type: 'float32'> | 0 |
319
+ | 316 | Constant_173040 | [4096,4096] | <Type: 'int8_t'> | 0.700204 |
320
+ | 317 | Constant_173042 | [4096,1] | <Type: 'float32'> | 0 |
321
+ | 318 | Constant_167364 | [1,1,4096] | <Type: 'float32'> | 0 |
322
+ | 319 | Constant_173044 | [16384,4096] | <Type: 'int8_t'> | 0.70015 |
323
+ | 320 | Constant_173046 | [16384,1] | <Type: 'float32'> | 0 |
324
+ | 321 | Constant_173048 | [4096,16384] | <Type: 'int8_t'> | 0.700184 |
325
+ | 322 | Constant_173050 | [4096,1] | <Type: 'float32'> | 0 |
326
+ | 323 | Constant_167381 | [1,1,4096] | <Type: 'float32'> | 0 |
327
+ | 324 | Constant_173052 | [50432,4096] | <Type: 'int8_t'> | 0.0132285 |
328
+ | 325 | Constant_173054 | [50432,1] | <Type: 'float32'> | 0 |
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/neuralmagic/mpt-7b-gsm8k-pt/w8a8-sparse70/tokenizer_config.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "model_max_length": 512,
209
+ "pad_token": "<|endoftext|>",
210
+ "tokenizer_class": "GPTNeoXTokenizer",
211
+ "unk_token": "<|endoftext|>"
212
+ }