Dongfu Jiang
commited on
Commit
•
fad1144
1
Parent(s):
b3f84d4
Upload 10 files
Browse files- added_tokens.json +7 -0
- config.bin +3 -0
- desktop.ini +0 -0
- pytorch_model.bin +3 -0
- ranker_config.json +19 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- 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 sha256:2c689ee2a644c7173ab8649bbd6d856c25ebba9825db9951145c1e66e403997e
|
| 3 |
+
size 687
|
desktop.ini
ADDED
|
Binary file (244 Bytes). View file
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b82e8cfba027b8a2f1b7f93f15887527c2aacb103fdebdd230a83073cfe72fe
|
| 3 |
+
size 1786165535
|
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": null,
|
| 6 |
+
"load_checkpoint": null,
|
| 7 |
+
"source_max_length": 128,
|
| 8 |
+
"candidate_max_length": 128,
|
| 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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[UNK]"
|
| 9 |
+
}
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3acd68d4fc46ad568d4bba0a878036b85755818a7179a426ec308b4d1d9c2df
|
| 3 |
+
size 3823
|