Upload folder using huggingface_hub
Browse files- README.md +165 -0
- config.json +26 -0
- mergekit_config.yml +136 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
README.md
ADDED
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# final_merge
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065 as a base.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
22 |
+
* ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
base_model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
30 |
+
dtype: bfloat16
|
31 |
+
merge_method: dare_ties
|
32 |
+
parameters:
|
33 |
+
int8_mask: 1.0
|
34 |
+
normalize: 1.0
|
35 |
+
slices:
|
36 |
+
- sources:
|
37 |
+
- layer_range: [0, 4]
|
38 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
39 |
+
parameters:
|
40 |
+
density: 0.6849374987082797
|
41 |
+
weight: 0.41688291356235085
|
42 |
+
- layer_range: [0, 4]
|
43 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
44 |
+
parameters:
|
45 |
+
density: 1.0
|
46 |
+
weight: 0.22402138180057965
|
47 |
+
- layer_range: [0, 4]
|
48 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
49 |
+
parameters:
|
50 |
+
density: 1.0
|
51 |
+
weight: 0.14273100451544973
|
52 |
+
- sources:
|
53 |
+
- layer_range: [4, 8]
|
54 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
55 |
+
parameters:
|
56 |
+
density: 1.0
|
57 |
+
weight: 0.27745773580979954
|
58 |
+
- layer_range: [4, 8]
|
59 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
60 |
+
parameters:
|
61 |
+
density: 0.8641797141160683
|
62 |
+
weight: 0.21900101081627826
|
63 |
+
- layer_range: [4, 8]
|
64 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
65 |
+
parameters:
|
66 |
+
density: 0.7045066746748807
|
67 |
+
weight: 0.27219079838557547
|
68 |
+
- sources:
|
69 |
+
- layer_range: [8, 12]
|
70 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
71 |
+
parameters:
|
72 |
+
density: 0.9344897829414548
|
73 |
+
weight: 0.39771623371112386
|
74 |
+
- layer_range: [8, 12]
|
75 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
76 |
+
parameters:
|
77 |
+
density: 1.0
|
78 |
+
weight: 0.5638393619932354
|
79 |
+
- layer_range: [8, 12]
|
80 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
81 |
+
parameters:
|
82 |
+
density: 1.0
|
83 |
+
weight: 0.45491072302164476
|
84 |
+
- sources:
|
85 |
+
- layer_range: [12, 16]
|
86 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
87 |
+
parameters:
|
88 |
+
density: 1.0
|
89 |
+
weight: 0.043782836287435234
|
90 |
+
- layer_range: [12, 16]
|
91 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
92 |
+
parameters:
|
93 |
+
density: 1.0
|
94 |
+
weight: 0.12905392091616227
|
95 |
+
- layer_range: [12, 16]
|
96 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
97 |
+
parameters:
|
98 |
+
density: 1.0
|
99 |
+
weight: 0.32911680921058395
|
100 |
+
- sources:
|
101 |
+
- layer_range: [16, 20]
|
102 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
103 |
+
parameters:
|
104 |
+
density: 1.0
|
105 |
+
weight: 0.33223757646195995
|
106 |
+
- layer_range: [16, 20]
|
107 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
108 |
+
parameters:
|
109 |
+
density: 1.0
|
110 |
+
weight: 0.21148775085590665
|
111 |
+
- layer_range: [16, 20]
|
112 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
113 |
+
parameters:
|
114 |
+
density: 1.0
|
115 |
+
weight: 0.3100840123708662
|
116 |
+
- sources:
|
117 |
+
- layer_range: [20, 24]
|
118 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
119 |
+
parameters:
|
120 |
+
density: 1.0
|
121 |
+
weight: 0.047668810469104206
|
122 |
+
- layer_range: [20, 24]
|
123 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
124 |
+
parameters:
|
125 |
+
density: 1.0
|
126 |
+
weight: 0.38364985576700883
|
127 |
+
- layer_range: [20, 24]
|
128 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
129 |
+
parameters:
|
130 |
+
density: 1.0
|
131 |
+
weight: 0.7458689345554008
|
132 |
+
- sources:
|
133 |
+
- layer_range: [24, 28]
|
134 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
135 |
+
parameters:
|
136 |
+
density: 1.0
|
137 |
+
weight: 0.6585871690360476
|
138 |
+
- layer_range: [24, 28]
|
139 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
140 |
+
parameters:
|
141 |
+
density: 1.0
|
142 |
+
weight: 0.11141636691846393
|
143 |
+
- layer_range: [24, 28]
|
144 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
145 |
+
parameters:
|
146 |
+
density: 1.0
|
147 |
+
weight: 0.6680264219734943
|
148 |
+
- sources:
|
149 |
+
- layer_range: [28, 32]
|
150 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
151 |
+
parameters:
|
152 |
+
density: 1.0
|
153 |
+
weight: 0.554815190090898
|
154 |
+
- layer_range: [28, 32]
|
155 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
156 |
+
parameters:
|
157 |
+
density: 1.0
|
158 |
+
weight: 0.38561479058158477
|
159 |
+
- layer_range: [28, 32]
|
160 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
161 |
+
parameters:
|
162 |
+
density: 0.9671800407644409
|
163 |
+
weight: 0.16533929845269846
|
164 |
+
tokenizer_source: base
|
165 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.40.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 42800
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
2 |
+
dtype: bfloat16
|
3 |
+
merge_method: dare_ties
|
4 |
+
parameters:
|
5 |
+
int8_mask: 1.0
|
6 |
+
normalize: 1.0
|
7 |
+
slices:
|
8 |
+
- sources:
|
9 |
+
- layer_range: [0, 4]
|
10 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
11 |
+
parameters:
|
12 |
+
density: 0.6849374987082797
|
13 |
+
weight: 0.41688291356235085
|
14 |
+
- layer_range: [0, 4]
|
15 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
16 |
+
parameters:
|
17 |
+
density: 1.0
|
18 |
+
weight: 0.22402138180057965
|
19 |
+
- layer_range: [0, 4]
|
20 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
21 |
+
parameters:
|
22 |
+
density: 1.0
|
23 |
+
weight: 0.14273100451544973
|
24 |
+
- sources:
|
25 |
+
- layer_range: [4, 8]
|
26 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
27 |
+
parameters:
|
28 |
+
density: 1.0
|
29 |
+
weight: 0.27745773580979954
|
30 |
+
- layer_range: [4, 8]
|
31 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
32 |
+
parameters:
|
33 |
+
density: 0.8641797141160683
|
34 |
+
weight: 0.21900101081627826
|
35 |
+
- layer_range: [4, 8]
|
36 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
37 |
+
parameters:
|
38 |
+
density: 0.7045066746748807
|
39 |
+
weight: 0.27219079838557547
|
40 |
+
- sources:
|
41 |
+
- layer_range: [8, 12]
|
42 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
43 |
+
parameters:
|
44 |
+
density: 0.9344897829414548
|
45 |
+
weight: 0.39771623371112386
|
46 |
+
- layer_range: [8, 12]
|
47 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
48 |
+
parameters:
|
49 |
+
density: 1.0
|
50 |
+
weight: 0.5638393619932354
|
51 |
+
- layer_range: [8, 12]
|
52 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
53 |
+
parameters:
|
54 |
+
density: 1.0
|
55 |
+
weight: 0.45491072302164476
|
56 |
+
- sources:
|
57 |
+
- layer_range: [12, 16]
|
58 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
59 |
+
parameters:
|
60 |
+
density: 1.0
|
61 |
+
weight: 0.043782836287435234
|
62 |
+
- layer_range: [12, 16]
|
63 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
64 |
+
parameters:
|
65 |
+
density: 1.0
|
66 |
+
weight: 0.12905392091616227
|
67 |
+
- layer_range: [12, 16]
|
68 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
69 |
+
parameters:
|
70 |
+
density: 1.0
|
71 |
+
weight: 0.32911680921058395
|
72 |
+
- sources:
|
73 |
+
- layer_range: [16, 20]
|
74 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
75 |
+
parameters:
|
76 |
+
density: 1.0
|
77 |
+
weight: 0.33223757646195995
|
78 |
+
- layer_range: [16, 20]
|
79 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
80 |
+
parameters:
|
81 |
+
density: 1.0
|
82 |
+
weight: 0.21148775085590665
|
83 |
+
- layer_range: [16, 20]
|
84 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
85 |
+
parameters:
|
86 |
+
density: 1.0
|
87 |
+
weight: 0.3100840123708662
|
88 |
+
- sources:
|
89 |
+
- layer_range: [20, 24]
|
90 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
91 |
+
parameters:
|
92 |
+
density: 1.0
|
93 |
+
weight: 0.047668810469104206
|
94 |
+
- layer_range: [20, 24]
|
95 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
96 |
+
parameters:
|
97 |
+
density: 1.0
|
98 |
+
weight: 0.38364985576700883
|
99 |
+
- layer_range: [20, 24]
|
100 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
101 |
+
parameters:
|
102 |
+
density: 1.0
|
103 |
+
weight: 0.7458689345554008
|
104 |
+
- sources:
|
105 |
+
- layer_range: [24, 28]
|
106 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
107 |
+
parameters:
|
108 |
+
density: 1.0
|
109 |
+
weight: 0.6585871690360476
|
110 |
+
- layer_range: [24, 28]
|
111 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
112 |
+
parameters:
|
113 |
+
density: 1.0
|
114 |
+
weight: 0.11141636691846393
|
115 |
+
- layer_range: [24, 28]
|
116 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
117 |
+
parameters:
|
118 |
+
density: 1.0
|
119 |
+
weight: 0.6680264219734943
|
120 |
+
- sources:
|
121 |
+
- layer_range: [28, 32]
|
122 |
+
model: ../evol_merge_storage/input_models/Swallow-MS-7b-v0.1_259979065
|
123 |
+
parameters:
|
124 |
+
density: 1.0
|
125 |
+
weight: 0.554815190090898
|
126 |
+
- layer_range: [28, 32]
|
127 |
+
model: ../evol_merge_storage/input_models/Starling-LM-7B-beta_581094980
|
128 |
+
parameters:
|
129 |
+
density: 1.0
|
130 |
+
weight: 0.38561479058158477
|
131 |
+
- layer_range: [28, 32]
|
132 |
+
model: ../evol_merge_storage/input_models/Mistral-7B-Instruct-v0.2_674785087
|
133 |
+
parameters:
|
134 |
+
density: 0.9671800407644409
|
135 |
+
weight: 0.16533929845269846
|
136 |
+
tokenizer_source: base
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ff9a78609cd1b2e4ef69dec44823c04a9af6b9c89f34126510d17eb1b0c5efe
|
3 |
+
size 9979410400
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29b7fbaf63f2b3c8fee1c9c6bf3aab579e82c7dfd17c73eca9ea39af5b42a755
|
3 |
+
size 4681034848
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14660411392}, "weight_map": {"lm_head.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
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 sha256:6239e68e91d052426ceac4b17aadca42c34f5b2067caee6b67d42105742c1f16
|
3 |
+
size 903208
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
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 |
+
},
|
31 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": null,
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|