Hugging Face's logo

LinWeizheDragon
/
ColBERT-v2

Transformers
Safetensors
English
flmr
ColBERT
Passage Retrieval
Model card Files
xet
Community
LinWeizheDragon commited on
Commit
1931ce4
·
verified ·
1 Parent(s): 3a424fe

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +41 -0
  2. context_tokenizer/special_tokens_map.json +37 -0
  3. context_tokenizer/tokenizer_config.json +58 -0
  4. context_tokenizer/vocab.txt +0 -0
  5. model.safetensors +3 -0
  6. query_tokenizer/special_tokens_map.json +37 -0
  7. query_tokenizer/tokenizer_config.json +59 -0
  8. query_tokenizer/vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FLMRModelForRetrieval"
4
+ ],
5
+ "context_concat_output_from_text_encoder": true,
6
+ "context_concat_output_from_vision_encoder": false,
7
+ "dim": 128,
8
+ "initializer_range": 0.02,
9
+ "load_cpu_extension": false,
10
+ "mapping_network_prefix_length": 32,
11
+ "mask_instruction_token": null,
12
+ "mask_punctuation": true,
13
+ "model_type": "flmr",
14
+ "query_concat_output_from_text_encoder": true,
15
+ "query_concat_output_from_vision_encoder": false,
16
+ "separate_query_and_context_text_encoder": false,
17
+ "separate_query_and_context_vision_encoder": false,
18
+ "text_config": {
19
+ "_name_or_path": "/future/u/okhattab/root/unit/experiments/2021.10/none/kld.v3.nway32.l2.ib/checkpoints/colbert-150000/",
20
+ "architectures": [
21
+ "HF_ColBERT"
22
+ ],
23
+ "classifier_dropout": null,
24
+ "gradient_checkpointing": false,
25
+ "model_type": "flmr_text_model",
26
+ "torch_dtype": "float32",
27
+ "use_cache": true
28
+ },
29
+ "torch_dtype": "float32",
30
+ "transformer_mapping_config_base": null,
31
+ "transformer_mapping_cross_attention_length": 32,
32
+ "transformer_mapping_num_hidden_layers": null,
33
+ "transformers_version": "4.38.0.dev0",
34
+ "use_transformer_mapping_network": false,
35
+ "use_vision_encoder": false,
36
+ "vision_config": {
37
+ "dropout": 0.0,
38
+ "model_type": "flmr_vision_model"
39
+ },
40
+ "vision_model_version": null
41
+ }
context_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
context_tokenizer/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
+ "doc_maxlen": 512,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "FLMRContextEncoderTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
context_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18de0c49ea3b2b14c2b83e34f838176bfdeeae7f5ca51401b98082d73c3cbae9
3
+ size 438350616
query_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
query_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "attend_to_mask_tokens": false,
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "query_maxlen": 32,
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "FLMRQueryEncoderTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
query_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff