tokenizer
Browse files- added_tokens.json +40 -0
- config.json +5 -5
- special_tokens_map.json +5 -0
- tokenizer_config.json +34 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257
|
40 |
+
}
|
config.json
CHANGED
@@ -10,18 +10,18 @@
|
|
10 |
"initializer_range": 0.02,
|
11 |
"layer_norm_epsilon": 1e-05,
|
12 |
"model_type": "gptj",
|
13 |
-
"n_embd":
|
14 |
"n_head": 16,
|
15 |
"n_inner": null,
|
16 |
-
"n_layer":
|
17 |
"n_positions": 2048,
|
18 |
"resid_pdrop": 0.0,
|
19 |
-
"rotary_dim":
|
20 |
"scale_attn_weights": true,
|
21 |
"tie_word_embeddings": false,
|
22 |
"tokenizer_class": "CodeGenTokenizer",
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.
|
25 |
"use_cache": true,
|
26 |
-
"vocab_size":
|
27 |
}
|
|
|
10 |
"initializer_range": 0.02,
|
11 |
"layer_norm_epsilon": 1e-05,
|
12 |
"model_type": "gptj",
|
13 |
+
"n_embd": 1024,
|
14 |
"n_head": 16,
|
15 |
"n_inner": null,
|
16 |
+
"n_layer": 20,
|
17 |
"n_positions": 2048,
|
18 |
"resid_pdrop": 0.0,
|
19 |
+
"rotary_dim": 32,
|
20 |
"scale_attn_weights": true,
|
21 |
"tie_word_embeddings": false,
|
22 |
"tokenizer_class": "CodeGenTokenizer",
|
23 |
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.25.1",
|
25 |
"use_cache": true,
|
26 |
+
"vocab_size": 51200
|
27 |
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"name_or_path": "Salesforce/codegen-350M-mono",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "CodeGenTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|