antoinelouis
commited on
Commit
•
89e576d
1
Parent(s):
87ef63b
New model
Browse files- config.json +1 -1
- dev_scores.csv +0 -2
- mmarco_smalldev_scores.csv +7 -0
- model.safetensors +2 -2
- pytorch_model.bin +0 -3
- special_tokens_map.json +42 -6
- tokenizer.json +2 -2
- tokenizer_config.json +44 -9
config.json
CHANGED
@@ -26,7 +26,7 @@
|
|
26 |
"pad_token_id": 1,
|
27 |
"position_embedding_type": "absolute",
|
28 |
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.
|
30 |
"type_vocab_size": 1,
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 250002
|
|
|
26 |
"pad_token_id": 1,
|
27 |
"position_embedding_type": "absolute",
|
28 |
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.36.2",
|
30 |
"type_vocab_size": 1,
|
31 |
"use_cache": true,
|
32 |
"vocab_size": 250002
|
dev_scores.csv
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
r-precision,mrr@10,recall@10,recall@20,recall@50,recall@100,model
|
2 |
-
34.37,51.01,82.23,90.60,96.45,98.40,crossencoder-mMiniLMv2-L12-H384-distilled-from-XLMR-Large-mmarcoFR
|
|
|
|
|
|
mmarco_smalldev_scores.csv
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch,steps,cutoff,mrr,recall,r-precision
|
2 |
+
0,20000,5,0.31482808022922637,0.474331423113658,0.2164278892072588
|
3 |
+
0,20000,10,0.3295776481557284,0.5841212989493793,0.2164278892072588
|
4 |
+
0,20000,20,0.3360876387514804,0.6780682903533906,0.2164278892072588
|
5 |
+
0,20000,50,0.33942255586759496,0.781769340974212,0.2164278892072588
|
6 |
+
0,20000,100,0.340362503027537,0.8473615090735436,0.2164278892072588
|
7 |
+
0,20000,500,0.34093065850613546,0.9603151862464183,0.2164278892072588
|
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 sha256:63ed43a0e3161e11545fbdff635b9f90746ce7b9762389606825f5d4c83aabda
|
3 |
+
size 470588492
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:21f4517d704c02c12c35e66e9b7217f1b7527aa85cde2509c62b29ca4f151593
|
3 |
-
size 470637749
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,25 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
@@ -9,7 +27,25 @@
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
-
"pad_token":
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
}
|
tokenizer.json
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 sha256:8dcca5f037c4beb22bb95e204a945e0640e93d283ce622febe906fdf25a146d9
|
3 |
+
size 17083009
|
tokenizer_config.json
CHANGED
@@ -1,17 +1,52 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
5 |
"eos_token": "</s>",
|
6 |
-
"mask_token":
|
7 |
-
|
8 |
-
"content": "<mask>",
|
9 |
-
"lstrip": true,
|
10 |
-
"normalized": true,
|
11 |
-
"rstrip": false,
|
12 |
-
"single_word": false
|
13 |
-
},
|
14 |
-
"model_max_length": 512,
|
15 |
"pad_token": "<pad>",
|
16 |
"sep_token": "</s>",
|
17 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
"bos_token": "<s>",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "<s>",
|
47 |
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 256,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
"pad_token": "<pad>",
|
51 |
"sep_token": "</s>",
|
52 |
"tokenizer_class": "XLMRobertaTokenizer",
|