Xenova HF staff commited on
Commit
01408ad
1 Parent(s): f864958

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Maykeye/TinyLLama-v0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 64,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 256,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 8,
16
+ "num_key_value_heads": 16,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "transformers_version": "4.33.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.33.0.dev0"
7
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3763f9f513b9e74e3163c414175648a32ecdd3f2c240dd1be551ade1a5d4e0
3
+ size 18831545
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21fae0af980af7f7e1005f1abc22a1ed9a3bdad62394fbd5dca2776237ca146
3
+ size 19185357
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c613274e7b4ae8030e565a49431e5ad5481fcd3774fca084da707af3b531dbed
3
+ size 5630131
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a72c0a623820aeab2791e41fa280611ef4bff6624bdedcbdb9248e62dcd8ec
3
+ size 5124152
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897f742e4735a8e4216b13f7a028ec3dfbf442b76d638f3672d68194705a1bef
3
+ size 18834082
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc9425c29c3586cfadecc5c8b091b54c02ff42a68b6c5e4805720105101e08ed
3
+ size 5126664
quantize_config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Reshape",
8
+ "Range",
9
+ "MatMul",
10
+ "Slice",
11
+ "Softmax",
12
+ "Squeeze",
13
+ "Neg",
14
+ "Where",
15
+ "Sqrt",
16
+ "Less",
17
+ "Constant",
18
+ "Transpose",
19
+ "Gather",
20
+ "Cast",
21
+ "Pow",
22
+ "If",
23
+ "Sub",
24
+ "Equal",
25
+ "Identity",
26
+ "Expand",
27
+ "Add",
28
+ "ConstantOfShape",
29
+ "Mul",
30
+ "Div",
31
+ "Concat",
32
+ "Unsqueeze",
33
+ "Shape",
34
+ "ReduceMean",
35
+ "Sigmoid"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_model_merged": {
40
+ "op_types": [
41
+ "Reshape",
42
+ "Range",
43
+ "MatMul",
44
+ "Slice",
45
+ "Softmax",
46
+ "Squeeze",
47
+ "Neg",
48
+ "Where",
49
+ "Sqrt",
50
+ "Less",
51
+ "Constant",
52
+ "Transpose",
53
+ "Gather",
54
+ "Cast",
55
+ "Pow",
56
+ "If",
57
+ "Sub",
58
+ "Equal",
59
+ "Identity",
60
+ "Expand",
61
+ "Add",
62
+ "ConstantOfShape",
63
+ "Mul",
64
+ "Div",
65
+ "Concat",
66
+ "Unsqueeze",
67
+ "Shape",
68
+ "ReduceMean",
69
+ "Sigmoid"
70
+ ],
71
+ "weight_type": "QInt8"
72
+ },
73
+ "decoder_with_past_model": {
74
+ "op_types": [
75
+ "Reshape",
76
+ "Range",
77
+ "MatMul",
78
+ "Slice",
79
+ "Softmax",
80
+ "Squeeze",
81
+ "Neg",
82
+ "Where",
83
+ "Sqrt",
84
+ "Constant",
85
+ "Transpose",
86
+ "Gather",
87
+ "Cast",
88
+ "Pow",
89
+ "If",
90
+ "Sub",
91
+ "Equal",
92
+ "Identity",
93
+ "Expand",
94
+ "Add",
95
+ "ConstantOfShape",
96
+ "Mul",
97
+ "Div",
98
+ "Concat",
99
+ "Unsqueeze",
100
+ "Shape",
101
+ "ReduceMean",
102
+ "Sigmoid"
103
+ ],
104
+ "weight_type": "QInt8"
105
+ }
106
+ }
107
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
3
+ size 534194
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "model_max_length": 2048,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "use_default_system_prompt": true
32
+ }