csclarkeV75 commited on
Commit
04a5f96
·
1 Parent(s): 4f17fc0

Added initial version of MARS Encoder

Browse files
CECorrelationEvaluator_qr-dev_results.csv ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ epoch,steps,Pearson_Correlation,Spearman_Correlation
2
+ 0,-1,0.7995245439207993,0.6101085726851492
3
+ 1,-1,0.818848196591943,0.6125101699388535
4
+ 2,-1,0.8218412832248984,0.6127352398765499
5
+ 3,-1,0.8060285162981113,0.6111382204076435
README.md CHANGED
@@ -1,3 +1,22 @@
1
  ---
2
  license: cc
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc
3
  ---
4
+ # MARS Encoder for Multi-agent Response Selection
5
+ This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class and is the model used in the paper [One Agent To Rule Them All: Towards Multi-agent Conversational AI](https://csclarke.com/assets/pdf/ACL_2022.pdf).
6
+
7
+ ## Training Data
8
+ This model was trained on the [BBAI dataset](https://github.com/ChrisIsKing/black-box-multi-agent-integation/tree/main/data). The model will predict a score between 0 and 1 ranking the correctness of a response to a user question from a conversational agent.
9
+
10
+
11
+ ## Usage and Performance
12
+
13
+ Pre-trained models can be used like this:
14
+ ```
15
+ from sentence_transformers import CrossEncoder
16
+ model = CrossEncoder('csclarke/MARS-Encoder')
17
+ scores = model.predict([('question 1', 'response 1'), ('question 1', 'response 2')])
18
+ ```
19
+
20
+ The model will predict scores for the pairs `('question 1', 'response 1'')` and `('question 1', 'response 2')`.
21
+
22
+ You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
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": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "transformers_version": "4.5.1",
29
+ "type_vocab_size": 1,
30
+ "use_cache": true,
31
+ "vocab_size": 50265
32
+ }
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 sha256:505f2b7f37e557aea3a7ae652ad519ebefd9712473143f234ca8cbd8febb3a94
3
+ size 498674098
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff