Upload 14 files
Browse files- added_tokens.json +40 -0
- config.json +42 -0
- generation_config.json +10 -0
- hash_record_sha256.json +50 -0
- openvino_detokenizer.bin +3 -0
- openvino_detokenizer.xml +97 -0
- openvino_model.xml +0 -0
- openvino_tokenizer.bin +3 -0
- openvino_tokenizer.xml +231 -0
- special_tokens_map.json +33 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +349 -0
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|/code|>": 32014,
|
3 |
+
"<|/data|>": 32033,
|
4 |
+
"<|/inst|>": 32037,
|
5 |
+
"<|/query|>": 32031,
|
6 |
+
"<|/sys|>": 32035,
|
7 |
+
"<|assistant_mask|>": 32017,
|
8 |
+
"<|assistant|>": 32001,
|
9 |
+
"<|calc|>": 32012,
|
10 |
+
"<|code|>": 32013,
|
11 |
+
"<|continue|>": 32009,
|
12 |
+
"<|data|>": 32032,
|
13 |
+
"<|diff_marker|>": 32025,
|
14 |
+
"<|disc_sep|>": 32029,
|
15 |
+
"<|disc_start|>": 32028,
|
16 |
+
"<|disc_thread|><|query|>": 32030,
|
17 |
+
"<|endoftext|>": 32000,
|
18 |
+
"<|end|>": 32007,
|
19 |
+
"<|fim_middle|>": 32021,
|
20 |
+
"<|fim_prefix|>": 32020,
|
21 |
+
"<|fim_suffix|>": 32022,
|
22 |
+
"<|function_call|>": 32005,
|
23 |
+
"<|function_list|>": 32011,
|
24 |
+
"<|function_output|>": 32003,
|
25 |
+
"<|ghissue|>": 32026,
|
26 |
+
"<|ghreview|>": 32027,
|
27 |
+
"<|inst|>": 32036,
|
28 |
+
"<|ipynb_marker|>": 32024,
|
29 |
+
"<|message|>": 32019,
|
30 |
+
"<|meta_start|>": 32023,
|
31 |
+
"<|raw|>": 32008,
|
32 |
+
"<|resource|>": 32016,
|
33 |
+
"<|start|>": 32018,
|
34 |
+
"<|step|>": 32002,
|
35 |
+
"<|summary|>": 32015,
|
36 |
+
"<|system|>": 32006,
|
37 |
+
"<|sys|>": 32034,
|
38 |
+
"<|tag|>": 32004,
|
39 |
+
"<|user|>": 32010
|
40 |
+
}
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "llmware/slim-summary-phi-3",
|
3 |
+
"aib_version": "model_archive_072424_phi3_summarize_eot_6",
|
4 |
+
"architectures": [
|
5 |
+
"Phi3ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_bias": false,
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
|
11 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
|
12 |
+
},
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"embd_pdrop": 0.0,
|
15 |
+
"eos_token_id": 32000,
|
16 |
+
"hidden_act": "silu",
|
17 |
+
"hidden_size": 3072,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 8192,
|
20 |
+
"max_position_embeddings": 4096,
|
21 |
+
"model_type": "phi3",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 32,
|
24 |
+
"num_key_value_heads": 32,
|
25 |
+
"original_max_position_embeddings": 4096,
|
26 |
+
"pad_token_id": 32000,
|
27 |
+
"resid_pdrop": 0.0,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": null,
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"sliding_window": 2047,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"trained": "custom training",
|
34 |
+
"training_comments": "phi3-38-summary-eot-072424-6",
|
35 |
+
"training_dataset": [
|
36 |
+
"summarize2_032124_eot_1_5974.jsonl"
|
37 |
+
],
|
38 |
+
"training_timestamp": "Wed Jul 24 11:30:10 2024",
|
39 |
+
"transformers_version": "4.41.2",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 32064
|
42 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": [
|
5 |
+
32000,
|
6 |
+
32007
|
7 |
+
],
|
8 |
+
"pad_token_id": 32000,
|
9 |
+
"transformers_version": "4.41.2"
|
10 |
+
}
|
hash_record_sha256.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"10158455398104230730.cl_cache": "aa7b063d9d0f89556595dc0db7112f57fc72730dc223a11188ce0791a4a049e4",
|
3 |
+
"10356021205630361428.cl_cache": "a302b123b0533d3c3940cc8eb18e16b1361fcda8ed0720ed6c5752ec165049b4",
|
4 |
+
"11960430187801635767.cl_cache": "fd86af045b8b57fbf9c98f1ea269cb4d6927d97d5649e96f34c1229ae0bdb139",
|
5 |
+
"12220008416992186874.cl_cache": "086083969166e2236641c10f1dda3bd58cb91355f43515b9ae57b7816a5c3d68",
|
6 |
+
"12491022070653493942.cl_cache": "aec88a4d1c8345dce169a8140d58dcdec90f115e218d1189eff0df5d1a691d3f",
|
7 |
+
"13478782897627348977.cl_cache": "bc36e50f9592c08fe079518e487af5b0107dfe2d4d19812d844c439121414004",
|
8 |
+
"13554085573973268955.cl_cache": "e2b3d7aeafb4ea7434de70cfb843faea2eda0a8fe6875288ea1eff85a6373fba",
|
9 |
+
"1369503952285004803.cl_cache": "b1e3396b616d4eb7267b0d8ffa9794cdc09d70c8660fa19ddd894e0fa260c75f",
|
10 |
+
"13996787936830972335.cl_cache": "9d78146c0fa50919d32e42868a4af02c24bd63ebc16dd564126cb6b77d649ec8",
|
11 |
+
"1596604237746042687.blob": "53b7ef0a18f8d045cecb28a47e86eaec92c19bc55a5a4f16519043eee3caea01",
|
12 |
+
"16013559403963528396.cl_cache": "db356ca8754384e288c5b0feb2d84420ace8f747bf1f1e8e75706dafad1ec5ab",
|
13 |
+
"16763274895828577765.cl_cache": "7edf6dcbe72704e0ba75f5477bd25486bc2dd43f295b94b59db69a140adec81f",
|
14 |
+
"17057819248123174357.cl_cache": "48a8394e4230da0c34c69f77a4fb3a17b3d7df627092199615bb897223bc532e",
|
15 |
+
"17241201940673546154.cl_cache": "89c7f3c99a027936fb9144073338922f79497b934615ca494777fd7f5d784bfb",
|
16 |
+
"1790420631157243714.cl_cache": "f962822abb9b3674b98a368487ed556f0d066cac530b9b3716d771c527acc69e",
|
17 |
+
"17912415656894965490.cl_cache": "c23621773c88c749f8d5e974354f9853bd986174de5335e583c060962d00ee9b",
|
18 |
+
"18425406304142639651.cl_cache": "749f3a8df9a6164f2343880e4ceacf15381d5278b043550f0dcb3bd33d14e699",
|
19 |
+
"1961299979340114348.cl_cache": "d2046d92627a6bbbef9ee77f23fca547388eb2e5b24e69789c4f0350e7ecaf42",
|
20 |
+
"2490283793109781502.cl_cache": "ad809d6d011ea8162e1f5ad69ef36092c97ac8c5228dd3def499edc9c4e257df",
|
21 |
+
"2988057519490477592.cl_cache": "4c800b66f11182f6a083559b8083e159ea5c705c661dc32a97f2d3888dcad06a",
|
22 |
+
"3035564998975493395.cl_cache": "05c5f116b58f3f0052f1befdd83b5a45a2c5a601f6a530806ea058cf896e7a71",
|
23 |
+
"3202048464753725830.cl_cache": "e4dccfa9d8be55707a3261025ac3a48db02a47be7069200e00dc43920b0eb7a7",
|
24 |
+
"3657412230478188205.cl_cache": "467ee9ec2468914abbbd7c07c48dd603086e8d746b8e4d10d7d57c3124324de8",
|
25 |
+
"5017985870279549188.cl_cache": "d5e499a08991ab55d3b8b1b2c24d7fe58ed4a53e0c195513877880ec931b3b2f",
|
26 |
+
"5245770289428366785.cl_cache": "72a72749aee9b297fa2ba37eb5a36e7f31343fa108b95c278e372364ce22beba",
|
27 |
+
"5411758822553378190.cl_cache": "b71c616a76178e82ddea79c815daa386236fc8c1506118c3451322580db09bce",
|
28 |
+
"573295667991143319.cl_cache": "80efeeadad35ae1a58978f9e058c69cadbc36323b6223b439341e7932c56e2d1",
|
29 |
+
"7108403470358601067.cl_cache": "17013330e02b1db49aaf29f2f7f33cd5d7e35a011d8f9615380016104e1e1cd2",
|
30 |
+
"7734636128102750636.cl_cache": "655f4026a589e9af1f2d3939198d79c985a4622eac9cecd057c1d4e4462ae370",
|
31 |
+
"7828399907612310370.cl_cache": "330e4cbc9733e35ac4bc738ad4fe14b8389bc13f17342dc46a35db5f86030229",
|
32 |
+
"7975488413534497659.cl_cache": "12c108fdfd5af94901bbda32653526e4999a3230bd9ef4491dd18af8ed7758a5",
|
33 |
+
"8452604528763337239.cl_cache": "c5135e867986393344391cf1ed34e3905b5d85ee1409ed5402c730b817cc00ac",
|
34 |
+
"9084728301640608858.cl_cache": "3add911fcf5d6c908b85c054ace22fb3cc98f912460f6f696c0d8dc68237f237",
|
35 |
+
"9986486564802383596.cl_cache": "6a08cf57bb90089f47b159ab4a519cbec86257fe34be1c9e47d2fc61120e3cd3",
|
36 |
+
"added_tokens.json": "7af7f1ff8a66841fa0bf4e1b4350d71caf111799c91bdd42272dca5545241796",
|
37 |
+
"config.json": "045f258fea18472e095b08f66137ea89fc3caeeff17fc654e6c6f1ab6047687f",
|
38 |
+
"generation_config.json": "bea05b249fe75006b6cb734c0bee478c20b3db68962bd90a442c574af31a9ffa",
|
39 |
+
"openvino_detokenizer.bin": "f11b42a41c9694e27832929f9dc97f663d7e811f705e219dec3361a9521a4009",
|
40 |
+
"openvino_detokenizer.xml": "3672e5730d0dac0ea70345533ea9b849a4c3cffac90a537cad50857c714a364a",
|
41 |
+
"openvino_model.bin": "c0d98f1ced24ffde3b589e570e8d20e22251558a07694a100935b35f28de89d2",
|
42 |
+
"openvino_model.xml": "7fe37b353299e8d29f748a12a2a77ed8d4c593f8256307050377202e2dd6d066",
|
43 |
+
"openvino_tokenizer.bin": "373cb59c30a5a5679a23cdfd128c2048e1a574dc0384d1f0316ec717481fd87c",
|
44 |
+
"openvino_tokenizer.xml": "ecf33d36a0f3211b17ee87e839d03f28bfee0df03c537ff28a9eff2eda80e028",
|
45 |
+
"special_tokens_map.json": "84efd40e1c3094f99f07b8a51e57faad59711164938f18a1f6b2c567fc82e4a7",
|
46 |
+
"tokenizer.json": "ef8af2aa4fb2460f062916c8c4c1a20a5076f7613d31b0e3166ccbae68894e68",
|
47 |
+
"tokenizer.model": "9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347",
|
48 |
+
"tokenizer_config.json": "aa672fe65c22e74675e39f8d052b961534729bbfb834cae8a4ea136d87486cf5",
|
49 |
+
"time_stamp": "2024-07-30_133919"
|
50 |
+
}
|
openvino_detokenizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f11b42a41c9694e27832929f9dc97f663d7e811f705e219dec3361a9521a4009
|
3 |
+
size 500584
|
openvino_detokenizer.xml
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0"?>
|
2 |
+
<net name="detokenizer" version="11">
|
3 |
+
<layers>
|
4 |
+
<layer id="0" name="Parameter_221835" type="Parameter" version="opset1">
|
5 |
+
<data shape="?,?" element_type="i64" />
|
6 |
+
<output>
|
7 |
+
<port id="0" precision="I64" names="Parameter_221835">
|
8 |
+
<dim>-1</dim>
|
9 |
+
<dim>-1</dim>
|
10 |
+
</port>
|
11 |
+
</output>
|
12 |
+
</layer>
|
13 |
+
<layer id="1" name="Constant_221815" type="Const" version="opset1">
|
14 |
+
<data element_type="u8" shape="500584" offset="0" size="500584" />
|
15 |
+
<output>
|
16 |
+
<port id="0" precision="U8">
|
17 |
+
<dim>500584</dim>
|
18 |
+
</port>
|
19 |
+
</output>
|
20 |
+
</layer>
|
21 |
+
<layer id="2" name="Convert_221845" type="Convert" version="opset1">
|
22 |
+
<data destination_type="i32" />
|
23 |
+
<input>
|
24 |
+
<port id="0" precision="I64">
|
25 |
+
<dim>-1</dim>
|
26 |
+
<dim>-1</dim>
|
27 |
+
</port>
|
28 |
+
</input>
|
29 |
+
<output>
|
30 |
+
<port id="1" precision="I32">
|
31 |
+
<dim>-1</dim>
|
32 |
+
<dim>-1</dim>
|
33 |
+
</port>
|
34 |
+
</output>
|
35 |
+
</layer>
|
36 |
+
<layer id="3" name="SentencepieceDetokenizer_221836" type="SentencepieceDetokenizer" version="extension">
|
37 |
+
<input>
|
38 |
+
<port id="0" precision="U8">
|
39 |
+
<dim>500584</dim>
|
40 |
+
</port>
|
41 |
+
<port id="1" precision="I32">
|
42 |
+
<dim>-1</dim>
|
43 |
+
<dim>-1</dim>
|
44 |
+
</port>
|
45 |
+
</input>
|
46 |
+
<output>
|
47 |
+
<port id="2" precision="I32">
|
48 |
+
<dim>-1</dim>
|
49 |
+
</port>
|
50 |
+
<port id="3" precision="I32">
|
51 |
+
<dim>-1</dim>
|
52 |
+
</port>
|
53 |
+
<port id="4" precision="U8">
|
54 |
+
<dim>-1</dim>
|
55 |
+
</port>
|
56 |
+
</output>
|
57 |
+
</layer>
|
58 |
+
<layer id="4" name="StringTensorPack_221837" type="StringTensorPack" version="extension">
|
59 |
+
<data mode="begins_ends" />
|
60 |
+
<input>
|
61 |
+
<port id="0" precision="I32">
|
62 |
+
<dim>-1</dim>
|
63 |
+
</port>
|
64 |
+
<port id="1" precision="I32">
|
65 |
+
<dim>-1</dim>
|
66 |
+
</port>
|
67 |
+
<port id="2" precision="U8">
|
68 |
+
<dim>-1</dim>
|
69 |
+
</port>
|
70 |
+
</input>
|
71 |
+
<output>
|
72 |
+
<port id="3" precision="STRING" names="string_output">
|
73 |
+
<dim>-1</dim>
|
74 |
+
</port>
|
75 |
+
</output>
|
76 |
+
</layer>
|
77 |
+
<layer id="5" name="Result_221838" type="Result" version="opset1">
|
78 |
+
<input>
|
79 |
+
<port id="0" precision="STRING">
|
80 |
+
<dim>-1</dim>
|
81 |
+
</port>
|
82 |
+
</input>
|
83 |
+
</layer>
|
84 |
+
</layers>
|
85 |
+
<edges>
|
86 |
+
<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
|
87 |
+
<edge from-layer="1" from-port="0" to-layer="3" to-port="0" />
|
88 |
+
<edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
|
89 |
+
<edge from-layer="3" from-port="2" to-layer="4" to-port="0" />
|
90 |
+
<edge from-layer="3" from-port="3" to-layer="4" to-port="1" />
|
91 |
+
<edge from-layer="3" from-port="4" to-layer="4" to-port="2" />
|
92 |
+
<edge from-layer="4" from-port="3" to-layer="5" to-port="0" />
|
93 |
+
</edges>
|
94 |
+
<rt_info>
|
95 |
+
<eos_token_id value="32000" />
|
96 |
+
</rt_info>
|
97 |
+
</net>
|
openvino_model.xml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
openvino_tokenizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:373cb59c30a5a5679a23cdfd128c2048e1a574dc0384d1f0316ec717481fd87c
|
3 |
+
size 500520
|
openvino_tokenizer.xml
ADDED
@@ -0,0 +1,231 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0"?>
|
2 |
+
<net name="tokenizer" version="11">
|
3 |
+
<layers>
|
4 |
+
<layer id="0" name="string_input" type="Parameter" version="opset1">
|
5 |
+
<data shape="?" element_type="string" />
|
6 |
+
<output>
|
7 |
+
<port id="0" precision="STRING" names="string_input">
|
8 |
+
<dim>-1</dim>
|
9 |
+
</port>
|
10 |
+
</output>
|
11 |
+
</layer>
|
12 |
+
<layer id="1" name="Constant_221821" type="Const" version="opset1">
|
13 |
+
<data element_type="i32" shape="" offset="0" size="4" />
|
14 |
+
<output>
|
15 |
+
<port id="0" precision="I32" />
|
16 |
+
</output>
|
17 |
+
</layer>
|
18 |
+
<layer id="2" name="Constant_221814" type="Const" version="opset1">
|
19 |
+
<data element_type="u8" shape="500508" offset="4" size="500508" />
|
20 |
+
<output>
|
21 |
+
<port id="0" precision="U8">
|
22 |
+
<dim>500508</dim>
|
23 |
+
</port>
|
24 |
+
</output>
|
25 |
+
</layer>
|
26 |
+
<layer id="3" name="SentencepieceTokenizer_221817" type="SentencepieceTokenizer" version="extension">
|
27 |
+
<data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="false" />
|
28 |
+
<input>
|
29 |
+
<port id="0" precision="U8">
|
30 |
+
<dim>500508</dim>
|
31 |
+
</port>
|
32 |
+
<port id="1" precision="STRING">
|
33 |
+
<dim>-1</dim>
|
34 |
+
</port>
|
35 |
+
</input>
|
36 |
+
<output>
|
37 |
+
<port id="2" precision="I64">
|
38 |
+
<dim>-1</dim>
|
39 |
+
<dim>2</dim>
|
40 |
+
</port>
|
41 |
+
<port id="3" precision="I32">
|
42 |
+
<dim>-1</dim>
|
43 |
+
</port>
|
44 |
+
<port id="4" precision="I64">
|
45 |
+
<dim>2</dim>
|
46 |
+
</port>
|
47 |
+
</output>
|
48 |
+
</layer>
|
49 |
+
<layer id="4" name="Broadcast_221822" type="Broadcast" version="opset3">
|
50 |
+
<data mode="numpy" />
|
51 |
+
<input>
|
52 |
+
<port id="0" precision="I32" />
|
53 |
+
<port id="1" precision="I64">
|
54 |
+
<dim>2</dim>
|
55 |
+
</port>
|
56 |
+
</input>
|
57 |
+
<output>
|
58 |
+
<port id="2" precision="I32">
|
59 |
+
<dim>-1</dim>
|
60 |
+
<dim>-1</dim>
|
61 |
+
</port>
|
62 |
+
</output>
|
63 |
+
</layer>
|
64 |
+
<layer id="5" name="Constant_221823" type="Const" version="opset1">
|
65 |
+
<data element_type="i32" shape="" offset="500512" size="4" />
|
66 |
+
<output>
|
67 |
+
<port id="0" precision="I32" />
|
68 |
+
</output>
|
69 |
+
</layer>
|
70 |
+
<layer id="6" name="ShapeOf_221824" type="ShapeOf" version="opset3">
|
71 |
+
<data output_type="i64" />
|
72 |
+
<input>
|
73 |
+
<port id="0" precision="I32">
|
74 |
+
<dim>-1</dim>
|
75 |
+
</port>
|
76 |
+
</input>
|
77 |
+
<output>
|
78 |
+
<port id="1" precision="I64">
|
79 |
+
<dim>1</dim>
|
80 |
+
</port>
|
81 |
+
</output>
|
82 |
+
</layer>
|
83 |
+
<layer id="7" name="Broadcast_221825" type="Broadcast" version="opset3">
|
84 |
+
<data mode="numpy" />
|
85 |
+
<input>
|
86 |
+
<port id="0" precision="I32" />
|
87 |
+
<port id="1" precision="I64">
|
88 |
+
<dim>1</dim>
|
89 |
+
</port>
|
90 |
+
</input>
|
91 |
+
<output>
|
92 |
+
<port id="2" precision="I32">
|
93 |
+
<dim>-1</dim>
|
94 |
+
</port>
|
95 |
+
</output>
|
96 |
+
</layer>
|
97 |
+
<layer id="8" name="ScatterNDUpdate_221829" type="ScatterNDUpdate" version="opset4">
|
98 |
+
<input>
|
99 |
+
<port id="0" precision="I32">
|
100 |
+
<dim>-1</dim>
|
101 |
+
<dim>-1</dim>
|
102 |
+
</port>
|
103 |
+
<port id="1" precision="I64">
|
104 |
+
<dim>-1</dim>
|
105 |
+
<dim>2</dim>
|
106 |
+
</port>
|
107 |
+
<port id="2" precision="I32">
|
108 |
+
<dim>-1</dim>
|
109 |
+
</port>
|
110 |
+
</input>
|
111 |
+
<output>
|
112 |
+
<port id="3" precision="I32">
|
113 |
+
<dim>-1</dim>
|
114 |
+
<dim>-1</dim>
|
115 |
+
</port>
|
116 |
+
</output>
|
117 |
+
</layer>
|
118 |
+
<layer id="9" name="ScatterNDUpdate_221829" type="Convert" version="opset1">
|
119 |
+
<data destination_type="i64" />
|
120 |
+
<input>
|
121 |
+
<port id="0" precision="I32">
|
122 |
+
<dim>-1</dim>
|
123 |
+
<dim>-1</dim>
|
124 |
+
</port>
|
125 |
+
</input>
|
126 |
+
<output>
|
127 |
+
<port id="1" precision="I64" names="attention_mask">
|
128 |
+
<dim>-1</dim>
|
129 |
+
<dim>-1</dim>
|
130 |
+
</port>
|
131 |
+
</output>
|
132 |
+
</layer>
|
133 |
+
<layer id="11" name="Constant_221818" type="Const" version="opset1">
|
134 |
+
<data element_type="i32" shape="" offset="500516" size="4" />
|
135 |
+
<output>
|
136 |
+
<port id="0" precision="I32" />
|
137 |
+
</output>
|
138 |
+
</layer>
|
139 |
+
<layer id="12" name="Broadcast_221819" type="Broadcast" version="opset3">
|
140 |
+
<data mode="numpy" />
|
141 |
+
<input>
|
142 |
+
<port id="0" precision="I32" />
|
143 |
+
<port id="1" precision="I64">
|
144 |
+
<dim>2</dim>
|
145 |
+
</port>
|
146 |
+
</input>
|
147 |
+
<output>
|
148 |
+
<port id="2" precision="I32">
|
149 |
+
<dim>-1</dim>
|
150 |
+
<dim>-1</dim>
|
151 |
+
</port>
|
152 |
+
</output>
|
153 |
+
</layer>
|
154 |
+
<layer id="13" name="ScatterNDUpdate_221820" type="ScatterNDUpdate" version="opset4">
|
155 |
+
<input>
|
156 |
+
<port id="0" precision="I32">
|
157 |
+
<dim>-1</dim>
|
158 |
+
<dim>-1</dim>
|
159 |
+
</port>
|
160 |
+
<port id="1" precision="I64">
|
161 |
+
<dim>-1</dim>
|
162 |
+
<dim>2</dim>
|
163 |
+
</port>
|
164 |
+
<port id="2" precision="I32">
|
165 |
+
<dim>-1</dim>
|
166 |
+
</port>
|
167 |
+
</input>
|
168 |
+
<output>
|
169 |
+
<port id="3" precision="I32">
|
170 |
+
<dim>-1</dim>
|
171 |
+
<dim>-1</dim>
|
172 |
+
</port>
|
173 |
+
</output>
|
174 |
+
</layer>
|
175 |
+
<layer id="14" name="ScatterNDUpdate_221820" type="Convert" version="opset1">
|
176 |
+
<data destination_type="i64" />
|
177 |
+
<input>
|
178 |
+
<port id="0" precision="I32">
|
179 |
+
<dim>-1</dim>
|
180 |
+
<dim>-1</dim>
|
181 |
+
</port>
|
182 |
+
</input>
|
183 |
+
<output>
|
184 |
+
<port id="1" precision="I64" names="input_ids">
|
185 |
+
<dim>-1</dim>
|
186 |
+
<dim>-1</dim>
|
187 |
+
</port>
|
188 |
+
</output>
|
189 |
+
</layer>
|
190 |
+
<layer id="15" name="Result_221830" type="Result" version="opset1">
|
191 |
+
<input>
|
192 |
+
<port id="0" precision="I64">
|
193 |
+
<dim>-1</dim>
|
194 |
+
<dim>-1</dim>
|
195 |
+
</port>
|
196 |
+
</input>
|
197 |
+
</layer>
|
198 |
+
<layer id="10" name="Result_221831" type="Result" version="opset1">
|
199 |
+
<input>
|
200 |
+
<port id="0" precision="I64">
|
201 |
+
<dim>-1</dim>
|
202 |
+
<dim>-1</dim>
|
203 |
+
</port>
|
204 |
+
</input>
|
205 |
+
</layer>
|
206 |
+
</layers>
|
207 |
+
<edges>
|
208 |
+
<edge from-layer="0" from-port="0" to-layer="3" to-port="1" />
|
209 |
+
<edge from-layer="1" from-port="0" to-layer="4" to-port="0" />
|
210 |
+
<edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
|
211 |
+
<edge from-layer="3" from-port="4" to-layer="4" to-port="1" />
|
212 |
+
<edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
|
213 |
+
<edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
|
214 |
+
<edge from-layer="3" from-port="4" to-layer="12" to-port="1" />
|
215 |
+
<edge from-layer="3" from-port="2" to-layer="13" to-port="1" />
|
216 |
+
<edge from-layer="3" from-port="3" to-layer="13" to-port="2" />
|
217 |
+
<edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
|
218 |
+
<edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
|
219 |
+
<edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
|
220 |
+
<edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
|
221 |
+
<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
|
222 |
+
<edge from-layer="9" from-port="1" to-layer="10" to-port="0" />
|
223 |
+
<edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
|
224 |
+
<edge from-layer="12" from-port="2" to-layer="13" to-port="0" />
|
225 |
+
<edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
|
226 |
+
<edge from-layer="14" from-port="1" to-layer="15" to-port="0" />
|
227 |
+
</edges>
|
228 |
+
<rt_info>
|
229 |
+
<eos_token_id value="32000" />
|
230 |
+
</rt_info>
|
231 |
+
</net>
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|/inst|>"
|
4 |
+
],
|
5 |
+
"bos_token": {
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"pad_token": {
|
20 |
+
"content": "<|endoftext|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,349 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|step|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|function_output|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|tag|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|function_call|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|raw|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|continue|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"32011": {
|
118 |
+
"content": "<|function_list|>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": true,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"32012": {
|
126 |
+
"content": "<|calc|>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": true,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"32013": {
|
134 |
+
"content": "<|code|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": true,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"32014": {
|
142 |
+
"content": "<|/code|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": true,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"32015": {
|
150 |
+
"content": "<|summary|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": true,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"32016": {
|
158 |
+
"content": "<|resource|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": true,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"32017": {
|
166 |
+
"content": "<|assistant_mask|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": true,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"32018": {
|
174 |
+
"content": "<|start|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": true,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"32019": {
|
182 |
+
"content": "<|message|>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": true,
|
186 |
+
"single_word": false,
|
187 |
+
"special": true
|
188 |
+
},
|
189 |
+
"32020": {
|
190 |
+
"content": "<|fim_prefix|>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": true,
|
194 |
+
"single_word": false,
|
195 |
+
"special": true
|
196 |
+
},
|
197 |
+
"32021": {
|
198 |
+
"content": "<|fim_middle|>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": true,
|
202 |
+
"single_word": false,
|
203 |
+
"special": true
|
204 |
+
},
|
205 |
+
"32022": {
|
206 |
+
"content": "<|fim_suffix|>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": true,
|
210 |
+
"single_word": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
"32023": {
|
214 |
+
"content": "<|meta_start|>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": true,
|
218 |
+
"single_word": false,
|
219 |
+
"special": true
|
220 |
+
},
|
221 |
+
"32024": {
|
222 |
+
"content": "<|ipynb_marker|>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": true,
|
226 |
+
"single_word": false,
|
227 |
+
"special": true
|
228 |
+
},
|
229 |
+
"32025": {
|
230 |
+
"content": "<|diff_marker|>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": true,
|
234 |
+
"single_word": false,
|
235 |
+
"special": true
|
236 |
+
},
|
237 |
+
"32026": {
|
238 |
+
"content": "<|ghissue|>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": true,
|
242 |
+
"single_word": false,
|
243 |
+
"special": true
|
244 |
+
},
|
245 |
+
"32027": {
|
246 |
+
"content": "<|ghreview|>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": true,
|
250 |
+
"single_word": false,
|
251 |
+
"special": true
|
252 |
+
},
|
253 |
+
"32028": {
|
254 |
+
"content": "<|disc_start|>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": true,
|
258 |
+
"single_word": false,
|
259 |
+
"special": true
|
260 |
+
},
|
261 |
+
"32029": {
|
262 |
+
"content": "<|disc_sep|>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": true,
|
266 |
+
"single_word": false,
|
267 |
+
"special": true
|
268 |
+
},
|
269 |
+
"32030": {
|
270 |
+
"content": "<|disc_thread|><|query|>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": true,
|
274 |
+
"single_word": false,
|
275 |
+
"special": true
|
276 |
+
},
|
277 |
+
"32031": {
|
278 |
+
"content": "<|/query|>",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": true,
|
282 |
+
"single_word": false,
|
283 |
+
"special": true
|
284 |
+
},
|
285 |
+
"32032": {
|
286 |
+
"content": "<|data|>",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": true,
|
290 |
+
"single_word": false,
|
291 |
+
"special": true
|
292 |
+
},
|
293 |
+
"32033": {
|
294 |
+
"content": "<|/data|>",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": true,
|
298 |
+
"single_word": false,
|
299 |
+
"special": true
|
300 |
+
},
|
301 |
+
"32034": {
|
302 |
+
"content": "<|sys|>",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": true,
|
306 |
+
"single_word": false,
|
307 |
+
"special": true
|
308 |
+
},
|
309 |
+
"32035": {
|
310 |
+
"content": "<|/sys|>",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": true,
|
314 |
+
"single_word": false,
|
315 |
+
"special": true
|
316 |
+
},
|
317 |
+
"32036": {
|
318 |
+
"content": "<|inst|>",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": true,
|
322 |
+
"single_word": false,
|
323 |
+
"special": true
|
324 |
+
},
|
325 |
+
"32037": {
|
326 |
+
"content": "<|/inst|>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": true,
|
330 |
+
"single_word": false,
|
331 |
+
"special": true
|
332 |
+
}
|
333 |
+
},
|
334 |
+
"additional_special_tokens": [
|
335 |
+
"<|/inst|>"
|
336 |
+
],
|
337 |
+
"bos_token": "<s>",
|
338 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
339 |
+
"clean_up_tokenization_spaces": false,
|
340 |
+
"eos_token": "<|endoftext|>",
|
341 |
+
"legacy": false,
|
342 |
+
"model_max_length": 4096,
|
343 |
+
"pad_token": "<|endoftext|>",
|
344 |
+
"padding_side": "left",
|
345 |
+
"sp_model_kwargs": {},
|
346 |
+
"tokenizer_class": "LlamaTokenizer",
|
347 |
+
"unk_token": "<unk>",
|
348 |
+
"use_default_system_prompt": false
|
349 |
+
}
|