Hugging Face's logo

Xenova
/
llama-160m

Text Generation
Transformers.js
ONNX
llama
Model card Files Community
Xenova HF staff commited on
Commit
7467b43
•
1 Parent(s): 4eade9f

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. config.json +26 -0
  2. generation_config.json +7 -0
  3. onnx/decoder_model.onnx +3 -0
  4. onnx/decoder_model_merged.onnx +3 -0
  5. onnx/decoder_model_merged_quantized.onnx +3 -0
  6. onnx/decoder_model_quantized.onnx +3 -0
  7. onnx/decoder_with_past_model.onnx +3 -0
  8. onnx/decoder_with_past_model_quantized.onnx +3 -0
  9. quantize_config.json +107 -0
  10. special_tokens_map.json +23 -0
  11. tokenizer.json +0 -0
  12. tokenizer.model +3 -0
  13. tokenizer_config.json +33 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llama-160m",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 12,
16
+ "num_key_value_heads": 12,
17
+ "pad_token_id": 1,
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": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
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 sha256:8794c19bf4b2cd9347ffd8ceaf997555fc277d9e5507d1801f7c6eebeae4ff5c
3
+ size 651138685
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52263c8e863f7424836373a393a878ef37767e8710aef0e4890e0a8edefa4254
3
+ size 652615520
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d5d80c77deb36b62c6cdbcefd73a9b1d9a44cf472c4b6649b279291014485e
3
+ size 165872190
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1dbc07281164359e0d7660770dbcedeac45c9145daba1b9714ffd7af7765a11
3
+ size 164170038
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5412a9162d87100830b60338a65b11edd6389f6525b95e0374c686280a7b246a
3
+ size 651145704
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868ffb0a14525787e2e6b32ce371d705e6ab29abcb93fe61a74cda3b0e65302
3
+ size 164178359
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
+ "Gather",
8
+ "Softmax",
9
+ "Where",
10
+ "Transpose",
11
+ "Expand",
12
+ "Reshape",
13
+ "Constant",
14
+ "Concat",
15
+ "Div",
16
+ "Cast",
17
+ "Identity",
18
+ "MatMul",
19
+ "Mul",
20
+ "ConstantOfShape",
21
+ "Sqrt",
22
+ "Slice",
23
+ "Less",
24
+ "If",
25
+ "Sigmoid",
26
+ "Unsqueeze",
27
+ "Add",
28
+ "Squeeze",
29
+ "ReduceMean",
30
+ "Neg",
31
+ "Range",
32
+ "Pow",
33
+ "Equal",
34
+ "Shape",
35
+ "Sub"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_model_merged": {
40
+ "op_types": [
41
+ "Gather",
42
+ "Softmax",
43
+ "Where",
44
+ "Transpose",
45
+ "Expand",
46
+ "Reshape",
47
+ "Constant",
48
+ "Concat",
49
+ "Div",
50
+ "Cast",
51
+ "Identity",
52
+ "MatMul",
53
+ "Mul",
54
+ "ConstantOfShape",
55
+ "Sqrt",
56
+ "Slice",
57
+ "Less",
58
+ "If",
59
+ "Sigmoid",
60
+ "Unsqueeze",
61
+ "Add",
62
+ "Squeeze",
63
+ "ReduceMean",
64
+ "Neg",
65
+ "Range",
66
+ "Pow",
67
+ "Equal",
68
+ "Shape",
69
+ "Sub"
70
+ ],
71
+ "weight_type": "QInt8"
72
+ },
73
+ "decoder_with_past_model": {
74
+ "op_types": [
75
+ "Gather",
76
+ "Softmax",
77
+ "Where",
78
+ "Transpose",
79
+ "Expand",
80
+ "Reshape",
81
+ "Constant",
82
+ "Concat",
83
+ "Div",
84
+ "Cast",
85
+ "Identity",
86
+ "MatMul",
87
+ "Mul",
88
+ "ConstantOfShape",
89
+ "Sqrt",
90
+ "Slice",
91
+ "If",
92
+ "Sigmoid",
93
+ "Unsqueeze",
94
+ "Add",
95
+ "Squeeze",
96
+ "ReduceMean",
97
+ "Neg",
98
+ "Range",
99
+ "Pow",
100
+ "Equal",
101
+ "Shape",
102
+ "Sub"
103
+ ],
104
+ "weight_type": "QInt8"
105
+ }
106
+ }
107
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "",
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000000000000019884624838656,
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
+ "use_fast": true
33
+ }