Wonder-Griffin
commited on
Upload folder using huggingface_hub
Browse files- config.json +1 -44
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -35
config.json
CHANGED
@@ -1,44 +1 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "C:/Users/wonde/output/Judge-GPT2",
|
3 |
-
"architectures": [
|
4 |
-
"JudgeModel"
|
5 |
-
],
|
6 |
-
"batch_size": 32,
|
7 |
-
"bias": true,
|
8 |
-
"block_size": 512,
|
9 |
-
"dim_feedforward": 3072,
|
10 |
-
"dropout": 0.1,
|
11 |
-
"ff_expansion_factor": 4,
|
12 |
-
"hidden_act": "gelu",
|
13 |
-
"hidden_size": 768,
|
14 |
-
"id2label": {
|
15 |
-
"0": "LABEL_0",
|
16 |
-
"1": "LABEL_1",
|
17 |
-
"2": "LABEL_2",
|
18 |
-
"3": "LABEL_3",
|
19 |
-
"4": "LABEL_4"
|
20 |
-
},
|
21 |
-
"label2id": {
|
22 |
-
"LABEL_0": 0,
|
23 |
-
"LABEL_1": 1,
|
24 |
-
"LABEL_2": 2,
|
25 |
-
"LABEL_3": 3,
|
26 |
-
"LABEL_4": 4
|
27 |
-
},
|
28 |
-
"label_smoothing": 0.1,
|
29 |
-
"learning_rate": 0.0003,
|
30 |
-
"log_interval": 100,
|
31 |
-
"max_grad_norm": 1.0,
|
32 |
-
"max_position_embeddings": 512,
|
33 |
-
"model_type": "judge-gpt",
|
34 |
-
"n_embd": 768,
|
35 |
-
"n_head": 12,
|
36 |
-
"n_layer": 12,
|
37 |
-
"output_dir": "C:/Users/wonde/output",
|
38 |
-
"torch_dtype": "float32",
|
39 |
-
"total_steps": 10000,
|
40 |
-
"transformers_version": "4.43.3",
|
41 |
-
"vocab_size": 50257,
|
42 |
-
"warmup_steps": 1000,
|
43 |
-
"weight_decay": 0.01
|
44 |
-
}
|
|
|
1 |
+
{"output_dir": "C:/Users/wonde/output", "vocab_size": 50257, "block_size": 512, "n_layer": 12, "n_head": 12, "n_embd": 768, "hidden_size": 768, "dropout": 0.1, "bias": true, "ff_expansion_factor": 4, "label_smoothing": 0.1}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01bdadeb4a7d84d93ebc5099dc624c424b5ef9be7c0031a60777221e293eea82
|
3 |
+
size 510026330
|
special_tokens_map.json
CHANGED
@@ -1,37 +1,7 @@
|
|
1 |
{
|
2 |
-
"cls_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
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 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|