Hugging Face's logo

LycheeMem
/
reranker

Text Classification
Transformers
Safetensors
bert
lycheemem
memory
reranking
evidence-retrieval
bert-tiny
Model card Files
xet
 Community
LycheeMem commited on
Commit
221f262
·
verified ·
1 Parent(s): 92c802b

Update model card with expanded zero-shot evaluation: LongMemEval-S, MSC-MemFuse-MC10, and HotpotQA. Checkpoint unchanged.

Browse files
Files changed (6) hide show
  1. config.json +31 -0
  2. model.safetensors +3 -0
  3. run_meta.json +56 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer_config.json +58 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 512,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 2,
23
+ "num_hidden_layers": 2,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "problem_type": "regression",
27
+ "transformers_version": "4.57.1",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 30522
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a328c53b55cbd49aeec0a44e6b9e2d02d09539e6784d93fc515ba815261fca0
3
+ size 17548796
run_meta.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "args": {
3
+ "bundle_cache": ".cache/probe_10s_all_memory_skipfusion.json",
4
+ "model_name": "prajjwal1/bert-tiny",
5
+ "top_k": 10,
6
+ "diagnose_top_k": 50,
7
+ "split": "interleave",
8
+ "train_fraction": 0.5,
9
+ "seed": 99,
10
+ "epochs": 3,
11
+ "batch_size": 16,
12
+ "score_batch_size": 64,
13
+ "lr": 2e-05,
14
+ "weight_decay": 0.01,
15
+ "max_len": 192,
16
+ "negatives_per_case": 16,
17
+ "max_pos_weight": 8.0,
18
+ "max_replacements": 1,
19
+ "margin_grid": [
20
+ 0.0
21
+ ],
22
+ "device": "cuda",
23
+ "save_model": ".cache/locomo_bert_tiny_reranker_10sall_seed99",
24
+ "progress_every": 125,
25
+ "print_margin_sweep": false,
26
+ "outcome_report": ".cache/transformer_outcomes_10sall_full_memory_seed99_saved.json",
27
+ "print_outcomes": 0
28
+ },
29
+ "metrics": {
30
+ "chosen_margin": 0.0,
31
+ "train": {
32
+ "cases": 766,
33
+ "baseline_hit": 465,
34
+ "wide_hit": 615,
35
+ "rank_or_topk_miss": 150,
36
+ "learned_top_hit": 537,
37
+ "learned_rank_or_topk_added": 98,
38
+ "merge_hit": 504,
39
+ "merge_added": 40,
40
+ "merge_lost": 1,
41
+ "merge_rank_or_topk_added": 40
42
+ },
43
+ "held": {
44
+ "cases": 765,
45
+ "baseline_hit": 466,
46
+ "wide_hit": 609,
47
+ "rank_or_topk_miss": 143,
48
+ "learned_top_hit": 507,
49
+ "learned_rank_or_topk_added": 90,
50
+ "merge_hit": 493,
51
+ "merge_added": 28,
52
+ "merge_lost": 1,
53
+ "merge_rank_or_topk_added": 28
54
+ }
55
+ }
56
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff