init
Browse files- README.md +202 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +130 -0
- special_tokens_map.json +160 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +1197 -0
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: speakleash/Bielik-11B-v2.0-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "speakleash/Bielik-11B-v2.0-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": [
|
18 |
+
"classifier",
|
19 |
+
"score"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj"
|
28 |
+
],
|
29 |
+
"task_type": "SEQ_CLS",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4da1108581bd7720308c0507633deeef55a8069be728e0e52b7d10980e2de21c
|
3 |
+
size 42715512
|
added_tokens.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|control_100|>": 32099,
|
3 |
+
"<|control_101|>": 32100,
|
4 |
+
"<|control_102|>": 32101,
|
5 |
+
"<|control_103|>": 32102,
|
6 |
+
"<|control_104|>": 32103,
|
7 |
+
"<|control_105|>": 32104,
|
8 |
+
"<|control_106|>": 32105,
|
9 |
+
"<|control_107|>": 32106,
|
10 |
+
"<|control_108|>": 32107,
|
11 |
+
"<|control_109|>": 32108,
|
12 |
+
"<|control_10|>": 32009,
|
13 |
+
"<|control_110|>": 32109,
|
14 |
+
"<|control_111|>": 32110,
|
15 |
+
"<|control_112|>": 32111,
|
16 |
+
"<|control_113|>": 32112,
|
17 |
+
"<|control_114|>": 32113,
|
18 |
+
"<|control_115|>": 32114,
|
19 |
+
"<|control_116|>": 32115,
|
20 |
+
"<|control_117|>": 32116,
|
21 |
+
"<|control_118|>": 32117,
|
22 |
+
"<|control_119|>": 32118,
|
23 |
+
"<|control_11|>": 32010,
|
24 |
+
"<|control_120|>": 32119,
|
25 |
+
"<|control_121|>": 32120,
|
26 |
+
"<|control_122|>": 32121,
|
27 |
+
"<|control_123|>": 32122,
|
28 |
+
"<|control_124|>": 32123,
|
29 |
+
"<|control_125|>": 32124,
|
30 |
+
"<|control_126|>": 32125,
|
31 |
+
"<|control_127|>": 32126,
|
32 |
+
"<|control_128|>": 32127,
|
33 |
+
"<|control_12|>": 32011,
|
34 |
+
"<|control_13|>": 32012,
|
35 |
+
"<|control_14|>": 32013,
|
36 |
+
"<|control_15|>": 32014,
|
37 |
+
"<|control_16|>": 32015,
|
38 |
+
"<|control_17|>": 32016,
|
39 |
+
"<|control_18|>": 32017,
|
40 |
+
"<|control_19|>": 32018,
|
41 |
+
"<|control_20|>": 32019,
|
42 |
+
"<|control_21|>": 32020,
|
43 |
+
"<|control_22|>": 32021,
|
44 |
+
"<|control_23|>": 32022,
|
45 |
+
"<|control_24|>": 32023,
|
46 |
+
"<|control_25|>": 32024,
|
47 |
+
"<|control_26|>": 32025,
|
48 |
+
"<|control_27|>": 32026,
|
49 |
+
"<|control_28|>": 32027,
|
50 |
+
"<|control_29|>": 32028,
|
51 |
+
"<|control_30|>": 32029,
|
52 |
+
"<|control_31|>": 32030,
|
53 |
+
"<|control_32|>": 32031,
|
54 |
+
"<|control_33|>": 32032,
|
55 |
+
"<|control_34|>": 32033,
|
56 |
+
"<|control_35|>": 32034,
|
57 |
+
"<|control_36|>": 32035,
|
58 |
+
"<|control_37|>": 32036,
|
59 |
+
"<|control_38|>": 32037,
|
60 |
+
"<|control_39|>": 32038,
|
61 |
+
"<|control_40|>": 32039,
|
62 |
+
"<|control_41|>": 32040,
|
63 |
+
"<|control_42|>": 32041,
|
64 |
+
"<|control_43|>": 32042,
|
65 |
+
"<|control_44|>": 32043,
|
66 |
+
"<|control_45|>": 32044,
|
67 |
+
"<|control_46|>": 32045,
|
68 |
+
"<|control_47|>": 32046,
|
69 |
+
"<|control_48|>": 32047,
|
70 |
+
"<|control_49|>": 32048,
|
71 |
+
"<|control_50|>": 32049,
|
72 |
+
"<|control_51|>": 32050,
|
73 |
+
"<|control_52|>": 32051,
|
74 |
+
"<|control_53|>": 32052,
|
75 |
+
"<|control_54|>": 32053,
|
76 |
+
"<|control_55|>": 32054,
|
77 |
+
"<|control_56|>": 32055,
|
78 |
+
"<|control_57|>": 32056,
|
79 |
+
"<|control_58|>": 32057,
|
80 |
+
"<|control_59|>": 32058,
|
81 |
+
"<|control_60|>": 32059,
|
82 |
+
"<|control_61|>": 32060,
|
83 |
+
"<|control_62|>": 32061,
|
84 |
+
"<|control_63|>": 32062,
|
85 |
+
"<|control_64|>": 32063,
|
86 |
+
"<|control_65|>": 32064,
|
87 |
+
"<|control_66|>": 32065,
|
88 |
+
"<|control_67|>": 32066,
|
89 |
+
"<|control_68|>": 32067,
|
90 |
+
"<|control_69|>": 32068,
|
91 |
+
"<|control_6|>": 32005,
|
92 |
+
"<|control_70|>": 32069,
|
93 |
+
"<|control_71|>": 32070,
|
94 |
+
"<|control_72|>": 32071,
|
95 |
+
"<|control_73|>": 32072,
|
96 |
+
"<|control_74|>": 32073,
|
97 |
+
"<|control_75|>": 32074,
|
98 |
+
"<|control_76|>": 32075,
|
99 |
+
"<|control_77|>": 32076,
|
100 |
+
"<|control_78|>": 32077,
|
101 |
+
"<|control_79|>": 32078,
|
102 |
+
"<|control_7|>": 32006,
|
103 |
+
"<|control_80|>": 32079,
|
104 |
+
"<|control_81|>": 32080,
|
105 |
+
"<|control_82|>": 32081,
|
106 |
+
"<|control_83|>": 32082,
|
107 |
+
"<|control_84|>": 32083,
|
108 |
+
"<|control_85|>": 32084,
|
109 |
+
"<|control_86|>": 32085,
|
110 |
+
"<|control_87|>": 32086,
|
111 |
+
"<|control_88|>": 32087,
|
112 |
+
"<|control_89|>": 32088,
|
113 |
+
"<|control_8|>": 32007,
|
114 |
+
"<|control_90|>": 32089,
|
115 |
+
"<|control_91|>": 32090,
|
116 |
+
"<|control_92|>": 32091,
|
117 |
+
"<|control_93|>": 32092,
|
118 |
+
"<|control_94|>": 32093,
|
119 |
+
"<|control_95|>": 32094,
|
120 |
+
"<|control_96|>": 32095,
|
121 |
+
"<|control_97|>": 32096,
|
122 |
+
"<|control_98|>": 32097,
|
123 |
+
"<|control_99|>": 32098,
|
124 |
+
"<|control_9|>": 32008,
|
125 |
+
"<|function_call|>": 32004,
|
126 |
+
"<|function_list|>": 32002,
|
127 |
+
"<|function_output|>": 32003,
|
128 |
+
"<|im_end|>": 32001,
|
129 |
+
"<|im_start|>": 32000
|
130 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|function_list|>",
|
6 |
+
"<|function_output|>",
|
7 |
+
"<|function_call|>",
|
8 |
+
"<|control_6|>",
|
9 |
+
"<|control_7|>",
|
10 |
+
"<|control_8|>",
|
11 |
+
"<|control_9|>",
|
12 |
+
"<|control_10|>",
|
13 |
+
"<|control_11|>",
|
14 |
+
"<|control_12|>",
|
15 |
+
"<|control_13|>",
|
16 |
+
"<|control_14|>",
|
17 |
+
"<|control_15|>",
|
18 |
+
"<|control_16|>",
|
19 |
+
"<|control_17|>",
|
20 |
+
"<|control_18|>",
|
21 |
+
"<|control_19|>",
|
22 |
+
"<|control_20|>",
|
23 |
+
"<|control_21|>",
|
24 |
+
"<|control_22|>",
|
25 |
+
"<|control_23|>",
|
26 |
+
"<|control_24|>",
|
27 |
+
"<|control_25|>",
|
28 |
+
"<|control_26|>",
|
29 |
+
"<|control_27|>",
|
30 |
+
"<|control_28|>",
|
31 |
+
"<|control_29|>",
|
32 |
+
"<|control_30|>",
|
33 |
+
"<|control_31|>",
|
34 |
+
"<|control_32|>",
|
35 |
+
"<|control_33|>",
|
36 |
+
"<|control_34|>",
|
37 |
+
"<|control_35|>",
|
38 |
+
"<|control_36|>",
|
39 |
+
"<|control_37|>",
|
40 |
+
"<|control_38|>",
|
41 |
+
"<|control_39|>",
|
42 |
+
"<|control_40|>",
|
43 |
+
"<|control_41|>",
|
44 |
+
"<|control_42|>",
|
45 |
+
"<|control_43|>",
|
46 |
+
"<|control_44|>",
|
47 |
+
"<|control_45|>",
|
48 |
+
"<|control_46|>",
|
49 |
+
"<|control_47|>",
|
50 |
+
"<|control_48|>",
|
51 |
+
"<|control_49|>",
|
52 |
+
"<|control_50|>",
|
53 |
+
"<|control_51|>",
|
54 |
+
"<|control_52|>",
|
55 |
+
"<|control_53|>",
|
56 |
+
"<|control_54|>",
|
57 |
+
"<|control_55|>",
|
58 |
+
"<|control_56|>",
|
59 |
+
"<|control_57|>",
|
60 |
+
"<|control_58|>",
|
61 |
+
"<|control_59|>",
|
62 |
+
"<|control_60|>",
|
63 |
+
"<|control_61|>",
|
64 |
+
"<|control_62|>",
|
65 |
+
"<|control_63|>",
|
66 |
+
"<|control_64|>",
|
67 |
+
"<|control_65|>",
|
68 |
+
"<|control_66|>",
|
69 |
+
"<|control_67|>",
|
70 |
+
"<|control_68|>",
|
71 |
+
"<|control_69|>",
|
72 |
+
"<|control_70|>",
|
73 |
+
"<|control_71|>",
|
74 |
+
"<|control_72|>",
|
75 |
+
"<|control_73|>",
|
76 |
+
"<|control_74|>",
|
77 |
+
"<|control_75|>",
|
78 |
+
"<|control_76|>",
|
79 |
+
"<|control_77|>",
|
80 |
+
"<|control_78|>",
|
81 |
+
"<|control_79|>",
|
82 |
+
"<|control_80|>",
|
83 |
+
"<|control_81|>",
|
84 |
+
"<|control_82|>",
|
85 |
+
"<|control_83|>",
|
86 |
+
"<|control_84|>",
|
87 |
+
"<|control_85|>",
|
88 |
+
"<|control_86|>",
|
89 |
+
"<|control_87|>",
|
90 |
+
"<|control_88|>",
|
91 |
+
"<|control_89|>",
|
92 |
+
"<|control_90|>",
|
93 |
+
"<|control_91|>",
|
94 |
+
"<|control_92|>",
|
95 |
+
"<|control_93|>",
|
96 |
+
"<|control_94|>",
|
97 |
+
"<|control_95|>",
|
98 |
+
"<|control_96|>",
|
99 |
+
"<|control_97|>",
|
100 |
+
"<|control_98|>",
|
101 |
+
"<|control_99|>",
|
102 |
+
"<|control_100|>",
|
103 |
+
"<|control_101|>",
|
104 |
+
"<|control_102|>",
|
105 |
+
"<|control_103|>",
|
106 |
+
"<|control_104|>",
|
107 |
+
"<|control_105|>",
|
108 |
+
"<|control_106|>",
|
109 |
+
"<|control_107|>",
|
110 |
+
"<|control_108|>",
|
111 |
+
"<|control_109|>",
|
112 |
+
"<|control_110|>",
|
113 |
+
"<|control_111|>",
|
114 |
+
"<|control_112|>",
|
115 |
+
"<|control_113|>",
|
116 |
+
"<|control_114|>",
|
117 |
+
"<|control_115|>",
|
118 |
+
"<|control_116|>",
|
119 |
+
"<|control_117|>",
|
120 |
+
"<|control_118|>",
|
121 |
+
"<|control_119|>",
|
122 |
+
"<|control_120|>",
|
123 |
+
"<|control_121|>",
|
124 |
+
"<|control_122|>",
|
125 |
+
"<|control_123|>",
|
126 |
+
"<|control_124|>",
|
127 |
+
"<|control_125|>",
|
128 |
+
"<|control_126|>",
|
129 |
+
"<|control_127|>",
|
130 |
+
"<|control_128|>"
|
131 |
+
],
|
132 |
+
"bos_token": {
|
133 |
+
"content": "<s>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false
|
138 |
+
},
|
139 |
+
"eos_token": {
|
140 |
+
"content": "<|im_end|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false
|
145 |
+
},
|
146 |
+
"pad_token": {
|
147 |
+
"content": "</s>",
|
148 |
+
"lstrip": false,
|
149 |
+
"normalized": false,
|
150 |
+
"rstrip": false,
|
151 |
+
"single_word": false
|
152 |
+
},
|
153 |
+
"unk_token": {
|
154 |
+
"content": "<unk>",
|
155 |
+
"lstrip": false,
|
156 |
+
"normalized": false,
|
157 |
+
"rstrip": false,
|
158 |
+
"single_word": false
|
159 |
+
}
|
160 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,1197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|im_start|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_end|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|function_list|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|function_output|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|function_call|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|control_6|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|control_7|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|control_8|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|control_9|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|control_10|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|control_11|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|control_12|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|control_13|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|control_14|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "<|control_15|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"32015": {
|
151 |
+
"content": "<|control_16|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"32016": {
|
159 |
+
"content": "<|control_17|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"32017": {
|
167 |
+
"content": "<|control_18|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"32018": {
|
175 |
+
"content": "<|control_19|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"32019": {
|
183 |
+
"content": "<|control_20|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"32020": {
|
191 |
+
"content": "<|control_21|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"32021": {
|
199 |
+
"content": "<|control_22|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"32022": {
|
207 |
+
"content": "<|control_23|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"32023": {
|
215 |
+
"content": "<|control_24|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"32024": {
|
223 |
+
"content": "<|control_25|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"32025": {
|
231 |
+
"content": "<|control_26|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"32026": {
|
239 |
+
"content": "<|control_27|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"32027": {
|
247 |
+
"content": "<|control_28|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"32028": {
|
255 |
+
"content": "<|control_29|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"32029": {
|
263 |
+
"content": "<|control_30|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"32030": {
|
271 |
+
"content": "<|control_31|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"32031": {
|
279 |
+
"content": "<|control_32|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"32032": {
|
287 |
+
"content": "<|control_33|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"32033": {
|
295 |
+
"content": "<|control_34|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"32034": {
|
303 |
+
"content": "<|control_35|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"32035": {
|
311 |
+
"content": "<|control_36|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"32036": {
|
319 |
+
"content": "<|control_37|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"32037": {
|
327 |
+
"content": "<|control_38|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"32038": {
|
335 |
+
"content": "<|control_39|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"32039": {
|
343 |
+
"content": "<|control_40|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"32040": {
|
351 |
+
"content": "<|control_41|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"32041": {
|
359 |
+
"content": "<|control_42|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"32042": {
|
367 |
+
"content": "<|control_43|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"32043": {
|
375 |
+
"content": "<|control_44|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"32044": {
|
383 |
+
"content": "<|control_45|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"32045": {
|
391 |
+
"content": "<|control_46|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"32046": {
|
399 |
+
"content": "<|control_47|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"32047": {
|
407 |
+
"content": "<|control_48|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"32048": {
|
415 |
+
"content": "<|control_49|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"32049": {
|
423 |
+
"content": "<|control_50|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"32050": {
|
431 |
+
"content": "<|control_51|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"32051": {
|
439 |
+
"content": "<|control_52|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"32052": {
|
447 |
+
"content": "<|control_53|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"32053": {
|
455 |
+
"content": "<|control_54|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"32054": {
|
463 |
+
"content": "<|control_55|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"32055": {
|
471 |
+
"content": "<|control_56|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"32056": {
|
479 |
+
"content": "<|control_57|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"32057": {
|
487 |
+
"content": "<|control_58|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"32058": {
|
495 |
+
"content": "<|control_59|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"32059": {
|
503 |
+
"content": "<|control_60|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"32060": {
|
511 |
+
"content": "<|control_61|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"32061": {
|
519 |
+
"content": "<|control_62|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"32062": {
|
527 |
+
"content": "<|control_63|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"32063": {
|
535 |
+
"content": "<|control_64|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"32064": {
|
543 |
+
"content": "<|control_65|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"32065": {
|
551 |
+
"content": "<|control_66|>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"32066": {
|
559 |
+
"content": "<|control_67|>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"32067": {
|
567 |
+
"content": "<|control_68|>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"32068": {
|
575 |
+
"content": "<|control_69|>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"32069": {
|
583 |
+
"content": "<|control_70|>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"32070": {
|
591 |
+
"content": "<|control_71|>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"32071": {
|
599 |
+
"content": "<|control_72|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"32072": {
|
607 |
+
"content": "<|control_73|>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"32073": {
|
615 |
+
"content": "<|control_74|>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"32074": {
|
623 |
+
"content": "<|control_75|>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"32075": {
|
631 |
+
"content": "<|control_76|>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"32076": {
|
639 |
+
"content": "<|control_77|>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"32077": {
|
647 |
+
"content": "<|control_78|>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"32078": {
|
655 |
+
"content": "<|control_79|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"32079": {
|
663 |
+
"content": "<|control_80|>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"32080": {
|
671 |
+
"content": "<|control_81|>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"32081": {
|
679 |
+
"content": "<|control_82|>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"32082": {
|
687 |
+
"content": "<|control_83|>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"32083": {
|
695 |
+
"content": "<|control_84|>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"32084": {
|
703 |
+
"content": "<|control_85|>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"32085": {
|
711 |
+
"content": "<|control_86|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"32086": {
|
719 |
+
"content": "<|control_87|>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"32087": {
|
727 |
+
"content": "<|control_88|>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"32088": {
|
735 |
+
"content": "<|control_89|>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"32089": {
|
743 |
+
"content": "<|control_90|>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"32090": {
|
751 |
+
"content": "<|control_91|>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"32091": {
|
759 |
+
"content": "<|control_92|>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"32092": {
|
767 |
+
"content": "<|control_93|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"32093": {
|
775 |
+
"content": "<|control_94|>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"32094": {
|
783 |
+
"content": "<|control_95|>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"32095": {
|
791 |
+
"content": "<|control_96|>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"32096": {
|
799 |
+
"content": "<|control_97|>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"32097": {
|
807 |
+
"content": "<|control_98|>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"32098": {
|
815 |
+
"content": "<|control_99|>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"32099": {
|
823 |
+
"content": "<|control_100|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"32100": {
|
831 |
+
"content": "<|control_101|>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
},
|
838 |
+
"32101": {
|
839 |
+
"content": "<|control_102|>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": true
|
845 |
+
},
|
846 |
+
"32102": {
|
847 |
+
"content": "<|control_103|>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": true
|
853 |
+
},
|
854 |
+
"32103": {
|
855 |
+
"content": "<|control_104|>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": true
|
861 |
+
},
|
862 |
+
"32104": {
|
863 |
+
"content": "<|control_105|>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": true
|
869 |
+
},
|
870 |
+
"32105": {
|
871 |
+
"content": "<|control_106|>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": true
|
877 |
+
},
|
878 |
+
"32106": {
|
879 |
+
"content": "<|control_107|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": true
|
885 |
+
},
|
886 |
+
"32107": {
|
887 |
+
"content": "<|control_108|>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": true
|
893 |
+
},
|
894 |
+
"32108": {
|
895 |
+
"content": "<|control_109|>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": true
|
901 |
+
},
|
902 |
+
"32109": {
|
903 |
+
"content": "<|control_110|>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": true
|
909 |
+
},
|
910 |
+
"32110": {
|
911 |
+
"content": "<|control_111|>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": true
|
917 |
+
},
|
918 |
+
"32111": {
|
919 |
+
"content": "<|control_112|>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": true
|
925 |
+
},
|
926 |
+
"32112": {
|
927 |
+
"content": "<|control_113|>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": true
|
933 |
+
},
|
934 |
+
"32113": {
|
935 |
+
"content": "<|control_114|>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
"32114": {
|
943 |
+
"content": "<|control_115|>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": true
|
949 |
+
},
|
950 |
+
"32115": {
|
951 |
+
"content": "<|control_116|>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": true
|
957 |
+
},
|
958 |
+
"32116": {
|
959 |
+
"content": "<|control_117|>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": true
|
965 |
+
},
|
966 |
+
"32117": {
|
967 |
+
"content": "<|control_118|>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": true
|
973 |
+
},
|
974 |
+
"32118": {
|
975 |
+
"content": "<|control_119|>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": true
|
981 |
+
},
|
982 |
+
"32119": {
|
983 |
+
"content": "<|control_120|>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": true
|
989 |
+
},
|
990 |
+
"32120": {
|
991 |
+
"content": "<|control_121|>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": true
|
997 |
+
},
|
998 |
+
"32121": {
|
999 |
+
"content": "<|control_122|>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": true
|
1005 |
+
},
|
1006 |
+
"32122": {
|
1007 |
+
"content": "<|control_123|>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": true
|
1013 |
+
},
|
1014 |
+
"32123": {
|
1015 |
+
"content": "<|control_124|>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": true
|
1021 |
+
},
|
1022 |
+
"32124": {
|
1023 |
+
"content": "<|control_125|>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": true
|
1029 |
+
},
|
1030 |
+
"32125": {
|
1031 |
+
"content": "<|control_126|>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": true
|
1037 |
+
},
|
1038 |
+
"32126": {
|
1039 |
+
"content": "<|control_127|>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": true
|
1045 |
+
},
|
1046 |
+
"32127": {
|
1047 |
+
"content": "<|control_128|>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": true
|
1053 |
+
}
|
1054 |
+
},
|
1055 |
+
"additional_special_tokens": [
|
1056 |
+
"<|im_start|>",
|
1057 |
+
"<|im_end|>",
|
1058 |
+
"<|function_list|>",
|
1059 |
+
"<|function_output|>",
|
1060 |
+
"<|function_call|>",
|
1061 |
+
"<|control_6|>",
|
1062 |
+
"<|control_7|>",
|
1063 |
+
"<|control_8|>",
|
1064 |
+
"<|control_9|>",
|
1065 |
+
"<|control_10|>",
|
1066 |
+
"<|control_11|>",
|
1067 |
+
"<|control_12|>",
|
1068 |
+
"<|control_13|>",
|
1069 |
+
"<|control_14|>",
|
1070 |
+
"<|control_15|>",
|
1071 |
+
"<|control_16|>",
|
1072 |
+
"<|control_17|>",
|
1073 |
+
"<|control_18|>",
|
1074 |
+
"<|control_19|>",
|
1075 |
+
"<|control_20|>",
|
1076 |
+
"<|control_21|>",
|
1077 |
+
"<|control_22|>",
|
1078 |
+
"<|control_23|>",
|
1079 |
+
"<|control_24|>",
|
1080 |
+
"<|control_25|>",
|
1081 |
+
"<|control_26|>",
|
1082 |
+
"<|control_27|>",
|
1083 |
+
"<|control_28|>",
|
1084 |
+
"<|control_29|>",
|
1085 |
+
"<|control_30|>",
|
1086 |
+
"<|control_31|>",
|
1087 |
+
"<|control_32|>",
|
1088 |
+
"<|control_33|>",
|
1089 |
+
"<|control_34|>",
|
1090 |
+
"<|control_35|>",
|
1091 |
+
"<|control_36|>",
|
1092 |
+
"<|control_37|>",
|
1093 |
+
"<|control_38|>",
|
1094 |
+
"<|control_39|>",
|
1095 |
+
"<|control_40|>",
|
1096 |
+
"<|control_41|>",
|
1097 |
+
"<|control_42|>",
|
1098 |
+
"<|control_43|>",
|
1099 |
+
"<|control_44|>",
|
1100 |
+
"<|control_45|>",
|
1101 |
+
"<|control_46|>",
|
1102 |
+
"<|control_47|>",
|
1103 |
+
"<|control_48|>",
|
1104 |
+
"<|control_49|>",
|
1105 |
+
"<|control_50|>",
|
1106 |
+
"<|control_51|>",
|
1107 |
+
"<|control_52|>",
|
1108 |
+
"<|control_53|>",
|
1109 |
+
"<|control_54|>",
|
1110 |
+
"<|control_55|>",
|
1111 |
+
"<|control_56|>",
|
1112 |
+
"<|control_57|>",
|
1113 |
+
"<|control_58|>",
|
1114 |
+
"<|control_59|>",
|
1115 |
+
"<|control_60|>",
|
1116 |
+
"<|control_61|>",
|
1117 |
+
"<|control_62|>",
|
1118 |
+
"<|control_63|>",
|
1119 |
+
"<|control_64|>",
|
1120 |
+
"<|control_65|>",
|
1121 |
+
"<|control_66|>",
|
1122 |
+
"<|control_67|>",
|
1123 |
+
"<|control_68|>",
|
1124 |
+
"<|control_69|>",
|
1125 |
+
"<|control_70|>",
|
1126 |
+
"<|control_71|>",
|
1127 |
+
"<|control_72|>",
|
1128 |
+
"<|control_73|>",
|
1129 |
+
"<|control_74|>",
|
1130 |
+
"<|control_75|>",
|
1131 |
+
"<|control_76|>",
|
1132 |
+
"<|control_77|>",
|
1133 |
+
"<|control_78|>",
|
1134 |
+
"<|control_79|>",
|
1135 |
+
"<|control_80|>",
|
1136 |
+
"<|control_81|>",
|
1137 |
+
"<|control_82|>",
|
1138 |
+
"<|control_83|>",
|
1139 |
+
"<|control_84|>",
|
1140 |
+
"<|control_85|>",
|
1141 |
+
"<|control_86|>",
|
1142 |
+
"<|control_87|>",
|
1143 |
+
"<|control_88|>",
|
1144 |
+
"<|control_89|>",
|
1145 |
+
"<|control_90|>",
|
1146 |
+
"<|control_91|>",
|
1147 |
+
"<|control_92|>",
|
1148 |
+
"<|control_93|>",
|
1149 |
+
"<|control_94|>",
|
1150 |
+
"<|control_95|>",
|
1151 |
+
"<|control_96|>",
|
1152 |
+
"<|control_97|>",
|
1153 |
+
"<|control_98|>",
|
1154 |
+
"<|control_99|>",
|
1155 |
+
"<|control_100|>",
|
1156 |
+
"<|control_101|>",
|
1157 |
+
"<|control_102|>",
|
1158 |
+
"<|control_103|>",
|
1159 |
+
"<|control_104|>",
|
1160 |
+
"<|control_105|>",
|
1161 |
+
"<|control_106|>",
|
1162 |
+
"<|control_107|>",
|
1163 |
+
"<|control_108|>",
|
1164 |
+
"<|control_109|>",
|
1165 |
+
"<|control_110|>",
|
1166 |
+
"<|control_111|>",
|
1167 |
+
"<|control_112|>",
|
1168 |
+
"<|control_113|>",
|
1169 |
+
"<|control_114|>",
|
1170 |
+
"<|control_115|>",
|
1171 |
+
"<|control_116|>",
|
1172 |
+
"<|control_117|>",
|
1173 |
+
"<|control_118|>",
|
1174 |
+
"<|control_119|>",
|
1175 |
+
"<|control_120|>",
|
1176 |
+
"<|control_121|>",
|
1177 |
+
"<|control_122|>",
|
1178 |
+
"<|control_123|>",
|
1179 |
+
"<|control_124|>",
|
1180 |
+
"<|control_125|>",
|
1181 |
+
"<|control_126|>",
|
1182 |
+
"<|control_127|>",
|
1183 |
+
"<|control_128|>"
|
1184 |
+
],
|
1185 |
+
"bos_token": "<s>",
|
1186 |
+
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
1187 |
+
"clean_up_tokenization_spaces": true,
|
1188 |
+
"eos_token": "<|im_end|>",
|
1189 |
+
"legacy": true,
|
1190 |
+
"model_max_length": 1000000000000000019884624838656,
|
1191 |
+
"pad_token": "</s>",
|
1192 |
+
"sp_model_kwargs": {},
|
1193 |
+
"spaces_between_special_tokens": false,
|
1194 |
+
"tokenizer_class": "LlamaTokenizer",
|
1195 |
+
"unk_token": "<unk>",
|
1196 |
+
"use_default_system_prompt": false
|
1197 |
+
}
|