add weights
Browse files- .gitattributes +1 -0
- merges.txt +0 -0
- model_config.json +48 -0
- model_state.pdparams +3 -0
- tokenizer_config.json +40 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
26 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
27 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
28 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
26 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
27 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
28 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*pdparams filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"init_args": [
|
3 |
+
{
|
4 |
+
"is_encoder": true,
|
5 |
+
"causal": false,
|
6 |
+
"n_langs": 15,
|
7 |
+
"use_lang_embeddings": true,
|
8 |
+
"vocab_size": 95000,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"pad_token_id": 2,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"num_attention_heads": 8,
|
13 |
+
"num_hidden_layers": 12,
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"attention_probs_dropout_prob": 0.1,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"use_sinusoidal_embeddings": false,
|
18 |
+
"layer_norm_eps": 1e-12,
|
19 |
+
"hidden_act": "gelu",
|
20 |
+
"embed_init_std": 0.02209708691207961,
|
21 |
+
"init_std": 0.02,
|
22 |
+
"use_asm": false,
|
23 |
+
"asm_cutoffs": 1,
|
24 |
+
"asm_div_value": 1,
|
25 |
+
"mask_token_id": 0,
|
26 |
+
"lang_id": 4,
|
27 |
+
"lang2id": {
|
28 |
+
"ar": 0,
|
29 |
+
"bg": 1,
|
30 |
+
"de": 2,
|
31 |
+
"el": 3,
|
32 |
+
"en": 4,
|
33 |
+
"es": 5,
|
34 |
+
"fr": 6,
|
35 |
+
"hi": 7,
|
36 |
+
"ru": 8,
|
37 |
+
"sw": 9,
|
38 |
+
"th": 10,
|
39 |
+
"tr": 11,
|
40 |
+
"ur": 12,
|
41 |
+
"vi": 13,
|
42 |
+
"zh": 14
|
43 |
+
},
|
44 |
+
"init_class": "XLMModel"
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"init_class": "XLMWithLMHeadModel"
|
48 |
+
}
|
model_state.pdparams
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a5127c74a7138693bfd3e56506e45afed0bdf19d4119ab20873af83164b46b3
|
3 |
+
size 498156169
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lowercase_and_remove_accent": true,
|
3 |
+
"id2lang": {
|
4 |
+
"0": "ar",
|
5 |
+
"1": "bg",
|
6 |
+
"2": "de",
|
7 |
+
"3": "el",
|
8 |
+
"4": "en",
|
9 |
+
"5": "es",
|
10 |
+
"6": "fr",
|
11 |
+
"7": "hi",
|
12 |
+
"8": "ru",
|
13 |
+
"9": "sw",
|
14 |
+
"10": "th",
|
15 |
+
"11": "tr",
|
16 |
+
"12": "ur",
|
17 |
+
"13": "vi",
|
18 |
+
"14": "zh"
|
19 |
+
},
|
20 |
+
"lang2id": {
|
21 |
+
"ar": 0,
|
22 |
+
"bg": 1,
|
23 |
+
"de": 2,
|
24 |
+
"el": 3,
|
25 |
+
"en": 4,
|
26 |
+
"es": 5,
|
27 |
+
"fr": 6,
|
28 |
+
"hi": 7,
|
29 |
+
"ru": 8,
|
30 |
+
"sw": 9,
|
31 |
+
"th": 10,
|
32 |
+
"tr": 11,
|
33 |
+
"ur": 12,
|
34 |
+
"vi": 13,
|
35 |
+
"zh": 14
|
36 |
+
},
|
37 |
+
"vocab_file": "C:\\Users\\yujun\\.paddlenlp\\models\\xlm-mlm-tlm-xnli15-1024\\vocab.json",
|
38 |
+
"merges_file": "C:\\Users\\yujun\\.paddlenlp\\models\\xlm-mlm-tlm-xnli15-1024\\merges.txt",
|
39 |
+
"init_class": "XLMTokenizer"
|
40 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|