Use BERTIN model
Browse files
config.json
CHANGED
@@ -7,21 +7,21 @@
|
|
7 |
"projection_dim": 512,
|
8 |
"seed": 42,
|
9 |
"text_config": {
|
10 |
-
"_name_or_path": "
|
11 |
"add_cross_attention": false,
|
12 |
"architectures": [
|
13 |
-
"
|
14 |
],
|
15 |
"attention_probs_dropout_prob": 0.1,
|
16 |
"bad_words_ids": null,
|
17 |
-
"bos_token_id":
|
18 |
"chunk_size_feed_forward": 0,
|
19 |
"decoder_start_token_id": null,
|
20 |
"diversity_penalty": 0.0,
|
21 |
"do_sample": false,
|
22 |
"early_stopping": false,
|
23 |
"encoder_no_repeat_ngram_size": 0,
|
24 |
-
"eos_token_id":
|
25 |
"finetuning_task": null,
|
26 |
"forced_bos_token_id": null,
|
27 |
"forced_eos_token_id": null,
|
@@ -41,12 +41,12 @@
|
|
41 |
"LABEL_0": 0,
|
42 |
"LABEL_1": 1
|
43 |
},
|
44 |
-
"layer_norm_eps": 1e-
|
45 |
"length_penalty": 1.0,
|
46 |
"max_length": 20,
|
47 |
-
"max_position_embeddings":
|
48 |
"min_length": 0,
|
49 |
-
"model_type": "
|
50 |
"no_repeat_ngram_size": 0,
|
51 |
"num_attention_heads": 12,
|
52 |
"num_beam_groups": 1,
|
@@ -55,7 +55,6 @@
|
|
55 |
"num_return_sequences": 1,
|
56 |
"output_attentions": false,
|
57 |
"output_hidden_states": false,
|
58 |
-
"output_past": true,
|
59 |
"output_scores": false,
|
60 |
"pad_token_id": 1,
|
61 |
"position_embedding_type": "absolute",
|
@@ -77,10 +76,10 @@
|
|
77 |
"torch_dtype": null,
|
78 |
"torchscript": false,
|
79 |
"transformers_version": "4.9.0.dev0",
|
80 |
-
"type_vocab_size":
|
81 |
"use_bfloat16": false,
|
82 |
"use_cache": true,
|
83 |
-
"vocab_size":
|
84 |
},
|
85 |
"transformers_version": null,
|
86 |
"vision_config": {
|
|
|
7 |
"projection_dim": 512,
|
8 |
"seed": 42,
|
9 |
"text_config": {
|
10 |
+
"_name_or_path": "",
|
11 |
"add_cross_attention": false,
|
12 |
"architectures": [
|
13 |
+
"RobertaForMaskedLM"
|
14 |
],
|
15 |
"attention_probs_dropout_prob": 0.1,
|
16 |
"bad_words_ids": null,
|
17 |
+
"bos_token_id": 0,
|
18 |
"chunk_size_feed_forward": 0,
|
19 |
"decoder_start_token_id": null,
|
20 |
"diversity_penalty": 0.0,
|
21 |
"do_sample": false,
|
22 |
"early_stopping": false,
|
23 |
"encoder_no_repeat_ngram_size": 0,
|
24 |
+
"eos_token_id": 2,
|
25 |
"finetuning_task": null,
|
26 |
"forced_bos_token_id": null,
|
27 |
"forced_eos_token_id": null,
|
|
|
41 |
"LABEL_0": 0,
|
42 |
"LABEL_1": 1
|
43 |
},
|
44 |
+
"layer_norm_eps": 1e-05,
|
45 |
"length_penalty": 1.0,
|
46 |
"max_length": 20,
|
47 |
+
"max_position_embeddings": 514,
|
48 |
"min_length": 0,
|
49 |
+
"model_type": "roberta",
|
50 |
"no_repeat_ngram_size": 0,
|
51 |
"num_attention_heads": 12,
|
52 |
"num_beam_groups": 1,
|
|
|
55 |
"num_return_sequences": 1,
|
56 |
"output_attentions": false,
|
57 |
"output_hidden_states": false,
|
|
|
58 |
"output_scores": false,
|
59 |
"pad_token_id": 1,
|
60 |
"position_embedding_type": "absolute",
|
|
|
76 |
"torch_dtype": null,
|
77 |
"torchscript": false,
|
78 |
"transformers_version": "4.9.0.dev0",
|
79 |
+
"type_vocab_size": 1,
|
80 |
"use_bfloat16": false,
|
81 |
"use_cache": true,
|
82 |
+
"vocab_size": 50265
|
83 |
},
|
84 |
"transformers_version": null,
|
85 |
"vision_config": {
|
flax_model.msgpack
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 sha256:55def72bbb5079de08c70573842ea2aa973f6c502d95505a9709e4cd2a2f6402
|
3 |
+
size 851566424
|
logs/events.out.tfevents.1626476231.t1v-n-5900a4fe-w-0.1105221.3.v2
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:14b7bc36e0d61b44077faab7a77617ee43c5c454bfcc1417c3741066482b2b93
|
3 |
-
size 1626638
|
|
|
|
|
|
|
|