End of training
Browse files- added_tokens.json +3 -0
- config.json +1 -1
- model.safetensors +2 -2
- special_tokens_map.json +7 -1
- tokenizer.json +9 -0
- tokenizer_config.json +9 -1
- training_args.bin +1 -1
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 49152
|
3 |
+
}
|
config.json
CHANGED
@@ -29,5 +29,5 @@
|
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.46.3",
|
31 |
"use_cache": true,
|
32 |
-
"vocab_size":
|
33 |
}
|
|
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.46.3",
|
31 |
"use_cache": true,
|
32 |
+
"vocab_size": 49153
|
33 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ad6614e360bd70103c94250d3be6603338e22bf0d5b1810fa0aec41d699e088
|
3 |
+
size 538092712
|
special_tokens_map.json
CHANGED
@@ -17,7 +17,13 @@
|
|
17 |
],
|
18 |
"bos_token": "<|im_start|>",
|
19 |
"eos_token": "<|im_end|>",
|
20 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"unk_token": {
|
22 |
"content": "<|endoftext|>",
|
23 |
"lstrip": false,
|
|
|
17 |
],
|
18 |
"bos_token": "<|im_start|>",
|
19 |
"eos_token": "<|im_end|>",
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
"unk_token": {
|
28 |
"content": "<|endoftext|>",
|
29 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -155,6 +155,15 @@
|
|
155 |
"rstrip": false,
|
156 |
"normalized": false,
|
157 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
158 |
}
|
159 |
],
|
160 |
"normalizer": null,
|
|
|
155 |
"rstrip": false,
|
156 |
"normalized": false,
|
157 |
"special": true
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"id": 49152,
|
161 |
+
"content": "<pad>",
|
162 |
+
"single_word": false,
|
163 |
+
"lstrip": false,
|
164 |
+
"rstrip": false,
|
165 |
+
"normalized": false,
|
166 |
+
"special": true
|
167 |
}
|
168 |
],
|
169 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -136,6 +136,14 @@
|
|
136 |
"rstrip": false,
|
137 |
"single_word": false,
|
138 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
139 |
}
|
140 |
},
|
141 |
"additional_special_tokens": [
|
@@ -147,7 +155,7 @@
|
|
147 |
"clean_up_tokenization_spaces": false,
|
148 |
"eos_token": "<|im_end|>",
|
149 |
"model_max_length": 8192,
|
150 |
-
"pad_token": "
|
151 |
"tokenizer_class": "GPT2Tokenizer",
|
152 |
"unk_token": "<|endoftext|>",
|
153 |
"vocab_size": 49152
|
|
|
136 |
"rstrip": false,
|
137 |
"single_word": false,
|
138 |
"special": true
|
139 |
+
},
|
140 |
+
"49152": {
|
141 |
+
"content": "<pad>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
}
|
148 |
},
|
149 |
"additional_special_tokens": [
|
|
|
155 |
"clean_up_tokenization_spaces": false,
|
156 |
"eos_token": "<|im_end|>",
|
157 |
"model_max_length": 8192,
|
158 |
+
"pad_token": "<pad>",
|
159 |
"tokenizer_class": "GPT2Tokenizer",
|
160 |
"unk_token": "<|endoftext|>",
|
161 |
"vocab_size": 49152
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6f65fdaceb5e16707c3865224e399060eb20a918078d4e2b2fc4ba7c99ac4a7
|
3 |
size 5560
|