Hugging Face's logo

llm-blender
/
PairRM

Text Generation
Transformers
Safetensors
English
deberta
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
Model card Files
xet
Community
4
Dongfu Jiang commited on
Commit
7b9ee76
·
1 Parent(s): d09aaea

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +7 -0
  2. config.bin +3 -0
  3. model.safetensors +3 -0
  4. ranker_config.json +19 -0
  5. special_tokens_map.json +15 -0
  6. spm.model +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +90 -0
  9. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|candidate1|>": 128002,
3
+ "<|candidate2|>": 128003,
4
+ "<|candidate|>": 128004,
5
+ "<|source|>": 128001,
6
+ "[MASK]": 128000
7
+ }
config.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20acae5188deb242477f61c3fbf0d5e7b9141c2249f92724bf777b9c2b636e42
3
+ size 1372
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c0e7e45732928610569a271ddbac4533839da3a469a010c7f10538414f5742
3
+ size 1744109020
ranker_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ranker_type": "pairranker",
3
+ "model_type": "deberta",
4
+ "model_name": "microsoft/deberta-v3-large",
5
+ "cache_dir": "./hf_models/deberta-v3-large/",
6
+ "load_checkpoint": null,
7
+ "source_maxlength": 1224,
8
+ "candidate_maxlength": 412,
9
+ "n_tasks": 1,
10
+ "num_pos": 5,
11
+ "num_neg": 5,
12
+ "sub_sampling_mode": "all_pair",
13
+ "sub_sampling_ratio": 0.4,
14
+ "loss_type": "instructgpt",
15
+ "reduce_type": "linear",
16
+ "inference_mode": "bubble",
17
+ "drop_out": 0.05,
18
+ "fp16": true
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128001": {
44
+ "content": "<|source|>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "128002": {
52
+ "content": "<|candidate1|>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "128003": {
60
+ "content": "<|candidate2|>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "128004": {
68
+ "content": "<|candidate|>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ }
75
+ },
76
+ "bos_token": "[CLS]",
77
+ "clean_up_tokenization_spaces": true,
78
+ "cls_token": "[CLS]",
79
+ "do_lower_case": false,
80
+ "eos_token": "[SEP]",
81
+ "mask_token": "[MASK]",
82
+ "model_max_length": 1000000000000000019884624838656,
83
+ "pad_token": "[PAD]",
84
+ "sep_token": "[SEP]",
85
+ "sp_model_kwargs": {},
86
+ "split_by_punct": false,
87
+ "tokenizer_class": "DebertaV2Tokenizer",
88
+ "unk_token": "[UNK]",
89
+ "vocab_type": "spm"
90
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c1bd75edeb1e61582b4b8f9a8fe1795e90edf81c95969c472e2afcd5160198
3
+ size 4792