debajyotidatta
commited on
Commit
•
0a6da74
1
Parent(s):
d12ddd0
Upload OPTForSequenceClassification
Browse files- config.json +46 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-350m",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForSequenceClassification"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": false,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 4096,
|
16 |
+
"hidden_size": 1024,
|
17 |
+
"id2label": {
|
18 |
+
"0": "expository",
|
19 |
+
"1": "procedural",
|
20 |
+
"2": "non_math",
|
21 |
+
"3": "probing_exploring",
|
22 |
+
"4": "other_math"
|
23 |
+
},
|
24 |
+
"init_std": 0.02,
|
25 |
+
"label2id": {
|
26 |
+
"expository": 0,
|
27 |
+
"non_math": 2,
|
28 |
+
"other_math": 4,
|
29 |
+
"probing_exploring": 3,
|
30 |
+
"procedural": 1
|
31 |
+
},
|
32 |
+
"layer_norm_elementwise_affine": true,
|
33 |
+
"layerdrop": 0.0,
|
34 |
+
"max_position_embeddings": 2048,
|
35 |
+
"model_type": "opt",
|
36 |
+
"num_attention_heads": 16,
|
37 |
+
"num_hidden_layers": 24,
|
38 |
+
"pad_token_id": 1,
|
39 |
+
"prefix": "</s>",
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.25.1",
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 50272,
|
45 |
+
"word_embed_proj_dim": 512
|
46 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f75c504e42289c8f0db8d65610552e1a0d68e33ff615d19c0f3f1e6d41e037bd
|
3 |
+
size 1324927713
|