Xenova HF staff commited on
Commit
15ebfa1
1 Parent(s): 01a2314

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "iliemihai/gpt-neo-romanian-125m",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 0,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 0,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "transformers_version": "4.33.0.dev0",
51
+ "use_cache": true,
52
+ "vocab_size": 64000,
53
+ "window_size": 256
54
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.33.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0990e474d3f0ac3e446d4e64265f4f774c29304d710ccebc32252be0fef9bb0
3
+ size 551697088
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015443a9746284cf866db6e1910874e076a3f6a0cdeba73d550b1636902c861f
3
+ size 560389302
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f07ffe79aab9dbcd57dec57ff55c685c5dbd65a4a1224bf4b7e37a6c2555110
3
+ size 153777081
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff060a1aa0d13a040ecc0e3bc785948b02aaa132ce29b297e858b5901c60eaae
3
+ size 144901731
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcaeef007f98966719b2892b3520719df4bb6717969dd47912a04448588f4e9
3
+ size 551704851
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5b28aa7edb4aa215cc19aaf6067060a4dc63befa385b4eb614e2a70c7b5d65
3
+ size 144911315
quantize_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Range",
8
+ "Concat",
9
+ "Pow",
10
+ "Slice",
11
+ "MatMul",
12
+ "Constant",
13
+ "ReduceMean",
14
+ "Where",
15
+ "Sub",
16
+ "Unsqueeze",
17
+ "Shape",
18
+ "Tanh",
19
+ "Reshape",
20
+ "Gather",
21
+ "Squeeze",
22
+ "Transpose",
23
+ "Div",
24
+ "Mul",
25
+ "Add",
26
+ "Cast",
27
+ "Sqrt",
28
+ "Softmax"
29
+ ],
30
+ "weight_type": "QInt8"
31
+ },
32
+ "decoder_model_merged": {
33
+ "op_types": [
34
+ "Range",
35
+ "Concat",
36
+ "Pow",
37
+ "Slice",
38
+ "MatMul",
39
+ "Constant",
40
+ "ReduceMean",
41
+ "Where",
42
+ "Sub",
43
+ "Unsqueeze",
44
+ "Shape",
45
+ "Tanh",
46
+ "Reshape",
47
+ "Gather",
48
+ "Squeeze",
49
+ "Transpose",
50
+ "Div",
51
+ "If",
52
+ "Mul",
53
+ "Add",
54
+ "Cast",
55
+ "Sqrt",
56
+ "Softmax"
57
+ ],
58
+ "weight_type": "QInt8"
59
+ },
60
+ "decoder_with_past_model": {
61
+ "op_types": [
62
+ "Range",
63
+ "Concat",
64
+ "Pow",
65
+ "Slice",
66
+ "MatMul",
67
+ "Constant",
68
+ "ReduceMean",
69
+ "Where",
70
+ "Sub",
71
+ "Unsqueeze",
72
+ "Shape",
73
+ "Tanh",
74
+ "Reshape",
75
+ "Gather",
76
+ "Squeeze",
77
+ "Transpose",
78
+ "Div",
79
+ "Add",
80
+ "Mul",
81
+ "Cast",
82
+ "Sqrt",
83
+ "Softmax"
84
+ ],
85
+ "weight_type": "QInt8"
86
+ }
87
+ }
88
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 2048,
22
+ "tokenizer_class": "GPT2Tokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff