v1: initial model (urgency threshold 0.97)
Browse files- config.json +28 -0
- label_config.json +42 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 6,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"transformers_version": "5.16.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
label_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"taxonomy_version": "2.0.0",
|
| 3 |
+
"domains": [
|
| 4 |
+
"entertainment_movies",
|
| 5 |
+
"sports",
|
| 6 |
+
"other"
|
| 7 |
+
],
|
| 8 |
+
"categories": [
|
| 9 |
+
"Box Office",
|
| 10 |
+
"Reviews",
|
| 11 |
+
"Releases & Trailers",
|
| 12 |
+
"Casting & Production",
|
| 13 |
+
"Awards & Festivals",
|
| 14 |
+
"Celebrity News",
|
| 15 |
+
"Streaming/OTT",
|
| 16 |
+
"Cricket",
|
| 17 |
+
"Football",
|
| 18 |
+
"Tennis",
|
| 19 |
+
"Basketball",
|
| 20 |
+
"Motorsport",
|
| 21 |
+
"Olympics & Other Sports",
|
| 22 |
+
"Other"
|
| 23 |
+
],
|
| 24 |
+
"category_to_domain": {
|
| 25 |
+
"Box Office": "entertainment_movies",
|
| 26 |
+
"Reviews": "entertainment_movies",
|
| 27 |
+
"Releases & Trailers": "entertainment_movies",
|
| 28 |
+
"Casting & Production": "entertainment_movies",
|
| 29 |
+
"Awards & Festivals": "entertainment_movies",
|
| 30 |
+
"Celebrity News": "entertainment_movies",
|
| 31 |
+
"Streaming/OTT": "entertainment_movies",
|
| 32 |
+
"Cricket": "sports",
|
| 33 |
+
"Football": "sports",
|
| 34 |
+
"Tennis": "sports",
|
| 35 |
+
"Basketball": "sports",
|
| 36 |
+
"Motorsport": "sports",
|
| 37 |
+
"Olympics & Other Sports": "sports",
|
| 38 |
+
"Other": "other"
|
| 39 |
+
},
|
| 40 |
+
"max_length": 256,
|
| 41 |
+
"urgency_threshold": 0.97
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32703a6a5d85e3750d28d67db24024321697c34b80400d1d56d1fd30d41ff63f
|
| 3 |
+
size 328545044
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"model_max_length": 512,
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 15 |
+
"trim_offsets": true,
|
| 16 |
+
"unk_token": "<unk>"
|
| 17 |
+
}
|