Hugging Face's logo

Xenova
/
llama-68m

Text Generation
Transformers.js
ONNX
llama
Model card Files
xet
Community
1
Xenova HF Staff commited on
Commit
01d3781
·
1 Parent(s): 1d5f9ed

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 +37 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llama-68m",
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": 2,
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 sha256:91d975800faf6443b376557b456fafd22d21a2a44267ab18deb78a9f3d3a20fd
3
+ size 273249997
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2702ba2c6d4352a6897dd68cdda2363a1008b6b62b3e207914ae4046d44b28c0
3
+ size 274375225
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a9b573443b21f461ac128a5fd4451ca6409bf44e23c10a670b9ac06924199d
3
+ size 70380772
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c8821072f1f953e544dc010b025c11b089cfca0a442fdabb59c296850fd1e3
3
+ size 69214310
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7c2b6bdbad71a407058a0865d4a12945d0fae80c4fb4682db97e04aa67d25b
3
+ size 273245876
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eaa4e15736ecbd355594d73a3c465d3b7a15c883594624d4e39780fc6586746
3
+ size 69208186
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
+ "Sub",
8
+ "Squeeze",
9
+ "ReduceMean",
10
+ "Constant",
11
+ "ConstantOfShape",
12
+ "Where",
13
+ "Softmax",
14
+ "Shape",
15
+ "Identity",
16
+ "Sqrt",
17
+ "Reshape",
18
+ "Transpose",
19
+ "Unsqueeze",
20
+ "Slice",
21
+ "Equal",
22
+ "Concat",
23
+ "Range",
24
+ "MatMul",
25
+ "Div",
26
+ "If",
27
+ "Sigmoid",
28
+ "Expand",
29
+ "Mul",
30
+ "Pow",
31
+ "Cast",
32
+ "Less",
33
+ "Neg",
34
+ "Gather",
35
+ "Add"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_model_merged": {
40
+ "op_types": [
41
+ "Sub",
42
+ "Squeeze",
43
+ "ReduceMean",
44
+ "Constant",
45
+ "ConstantOfShape",
46
+ "Where",
47
+ "Softmax",
48
+ "Shape",
49
+ "Identity",
50
+ "Sqrt",
51
+ "Reshape",
52
+ "Transpose",
53
+ "Unsqueeze",
54
+ "Slice",
55
+ "Equal",
56
+ "Concat",
57
+ "Range",
58
+ "MatMul",
59
+ "Div",
60
+ "If",
61
+ "Sigmoid",
62
+ "Expand",
63
+ "Mul",
64
+ "Pow",
65
+ "Cast",
66
+ "Less",
67
+ "Neg",
68
+ "Gather",
69
+ "Add"
70
+ ],
71
+ "weight_type": "QInt8"
72
+ },
73
+ "decoder_with_past_model": {
74
+ "op_types": [
75
+ "Sub",
76
+ "ReduceMean",
77
+ "Squeeze",
78
+ "Constant",
79
+ "ConstantOfShape",
80
+ "Where",
81
+ "Softmax",
82
+ "Shape",
83
+ "Identity",
84
+ "Sqrt",
85
+ "Reshape",
86
+ "Transpose",
87
+ "Unsqueeze",
88
+ "Slice",
89
+ "Equal",
90
+ "Concat",
91
+ "Range",
92
+ "MatMul",
93
+ "Div",
94
+ "If",
95
+ "Sigmoid",
96
+ "Expand",
97
+ "Mul",
98
+ "Pow",
99
+ "Cast",
100
+ "Neg",
101
+ "Gather",
102
+ "Add"
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "spaces_between_special_tokens": false,
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "use_default_system_prompt": true,
36
+ "use_fast": true
37
+ }