AbrahamSanders commited on
Commit
29a4358
1 Parent(s): 3a74fb2

First model version

Browse files
README.md CHANGED
@@ -1,3 +1,14 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ Base model: [lacai/roberta-large-dialog-narrative](https://huggingface.co/lacai/roberta-large-dialog-narrative)
6
+
7
+ Fine tuned as a progression model (to predict the acceptability of a dialogue) on the [Persuasion For Good Dataset](https://gitlab.com/ucdavisnlp/persuasionforgood) (Wang et al., 2019):
8
+
9
+ Given a complete dialogue from (or in the style of) Persuasion For Good, the task is to predict a numeric score typically in the range (-3, 3) where a higher score means a more acceptable dialogue in context of the donation solicitation task.
10
+ This model inherits a special dialogue token `<d>` from its base model, which indicates the start of a dialogue utterance.
11
+
12
+ **Example input**: `<d>How are you?</s><d>Good! how about yourself?</s><d>Great. Would you like to donate today to help the children?</s>`
13
+
14
+ For more context and usage information see [https://github.rpi.edu/LACAI/dialogue-progression](https://github.rpi.edu/LACAI/dialogue-progression).
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<n>": 50265, "<d>": 50266}
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lacai/roberta-large-dialog-narrative",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "roberta",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "regression",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.11.3",
31
+ "type_vocab_size": 1,
32
+ "use_cache": true,
33
+ "vocab_size": 50267
34
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197cc3f172570b449626413c24ec0ce768d339101b28827c3310b182576a50cb
3
+ size 1421615405
runs/events.out.tfevents.1649260060.panacea.41627.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704ccd86ab464dc99bb1bea9f384d9230a60d7444de543462a8c1b5250d3e513
3
+ size 58677
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<n>", "<d>"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "use_fast": true, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/deyd/.cache/huggingface/transformers/e16a2590deb9e6d73711d6e05bf27d832fa8c1162d807222e043ca650a556964.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "lacai/roberta-large-dialog-narrative", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff