Hugging Face's logo

Xenova
/
llama2.c-stories110M

Text Generation
Transformers.js
PyTorch
ONNX
Safetensors
Transformers
llama
text-generation-inference
Model card Files
xet
Community
4
Xenova HF Staff commited on
Commit
ab7316a
·
1 Parent(s): 556e41d

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +1 -0
  2. onnx/decoder_model.onnx +2 -2
  3. onnx/decoder_model_merged.onnx +2 -2
  4. onnx/decoder_model_merged_quantized.onnx +2 -2
  5. onnx/decoder_model_quantized.onnx +2 -2
  6. onnx/decoder_with_past_model.onnx +2 -2
  7. onnx/decoder_with_past_model_quantized.onnx +2 -2
  8. quantize_config.json +61 -62
  9. special_tokens_map.json +3 -21
  10. tokenizer_config.json +29 -23
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
 
1
  {
2
+ "_name_or_path": "Xenova/llama2.c-stories110M",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:518f877e2dccc56ad030d9720872f2ac692b61835e31e116ffb285582384c623
3
- size 537368189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4055de40adc6080300cb0a1a8986259c228b2447689651d7ce91ce340380b6
3
+ size 439063717
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d591ab765b32cfefa5586ac7a7b5577240195902b70e39c903d9bac4f1acd4b0
3
- size 538320735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27b7753ee0c8f83371ce28ebe01b94cddf93cc1045a9171623dc03d3b561c38
3
+ size 440015873
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4fb65533cebf47090f460b15dfadf306db447e9ec5bcf3735f6299e59a020ea
3
- size 136511989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a4a3b603720730b5d126fe18fb61f68ca137903881ca3d84db3bb0776d11d8
3
+ size 111933644
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ca251aacafd0bc97b73272fa713f888b84507269c83a85420f17af2fa595bd5
3
- size 135334125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c5f19b29fc636f5975f964289fc67d23039120b6479969746c7d51d36f2574
3
+ size 110756863
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b700555c3d04fa980bd6a55518ed2474f47e7bd9dfb60ace122e9d61694a471
3
- size 537375208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4194c70db527ebd117f4e530341522136e8c6322c86d9ff9cbff875da26c577
3
+ size 439070831
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:405c4a5918d015b814a8e94f4c19c31c6eee15579e71c9b23dd25bcaef48d75c
3
- size 135342446
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4a9d9b0e56de9f578abc299639909b3cca9258b87a55d0ef3ef9ae5ede0a55
3
+ size 110765314
quantize_config.json CHANGED
@@ -2,104 +2,103 @@
2
  "per_channel": false,
3
  "reduce_range": false,
4
  "per_model_config": {
5
- "decoder_model": {
6
  "op_types": [
7
- "Concat",
8
- "Where",
9
- "Less",
10
- "ConstantOfShape",
11
- "Neg",
12
- "Sqrt",
13
  "Div",
14
- "Softmax",
15
  "MatMul",
16
- "Slice",
17
- "Reshape",
18
- "Shape",
19
  "Pow",
20
- "Cast",
21
- "Equal",
 
 
22
  "Add",
 
 
 
23
  "Expand",
24
- "Mul",
25
- "Sub",
 
26
  "Gather",
27
- "Identity",
28
- "Range",
29
  "Transpose",
30
- "Constant",
31
- "Squeeze",
32
  "If",
33
- "ReduceMean",
34
- "Sigmoid",
35
- "Unsqueeze"
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
- "decoder_with_past_model": {
40
  "op_types": [
41
- "Concat",
42
- "Where",
43
- "ConstantOfShape",
44
- "Neg",
45
- "Sqrt",
 
46
  "Div",
47
- "Softmax",
48
  "MatMul",
49
- "Slice",
50
- "Reshape",
51
- "Shape",
52
  "Pow",
53
- "Cast",
54
- "Equal",
 
 
55
  "Add",
 
 
 
56
  "Expand",
57
- "Mul",
58
- "Sub",
 
 
59
  "Gather",
60
- "Identity",
61
  "Range",
62
  "Transpose",
63
- "Constant",
64
- "Squeeze",
65
  "If",
66
- "ReduceMean",
67
- "Sigmoid",
68
- "Unsqueeze"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_model_merged": {
73
  "op_types": [
74
- "Concat",
75
- "Where",
76
- "Less",
77
- "ConstantOfShape",
78
- "Neg",
79
- "Sqrt",
80
  "Div",
81
- "Softmax",
82
  "MatMul",
83
- "Slice",
84
- "Reshape",
85
- "Shape",
86
  "Pow",
87
- "Cast",
88
- "Equal",
 
 
89
  "Add",
 
 
 
90
  "Expand",
91
- "Mul",
92
- "Sub",
 
 
93
  "Gather",
94
- "Identity",
95
  "Range",
96
  "Transpose",
97
- "Constant",
98
- "Squeeze",
99
  "If",
100
- "ReduceMean",
101
- "Sigmoid",
102
- "Unsqueeze"
103
  ],
104
  "weight_type": "QInt8"
105
  }
 
2
  "per_channel": false,
3
  "reduce_range": false,
4
  "per_model_config": {
5
+ "decoder_with_past_model": {
6
  "op_types": [
7
+ "Sub",
8
+ "Slice",
9
+ "Constant",
10
+ "Identity",
11
+ "Equal",
12
+ "Sigmoid",
13
  "Div",
14
+ "Mul",
15
  "MatMul",
 
 
 
16
  "Pow",
17
+ "Where",
18
+ "Neg",
19
+ "ConstantOfShape",
20
+ "Softmax",
21
  "Add",
22
+ "Sqrt",
23
+ "Unsqueeze",
24
+ "Reshape",
25
  "Expand",
26
+ "ReduceMean",
27
+ "Concat",
28
+ "Cast",
29
  "Gather",
 
 
30
  "Transpose",
31
+ "Shape",
 
32
  "If",
33
+ "Squeeze"
 
 
34
  ],
35
  "weight_type": "QInt8"
36
  },
37
+ "decoder_model": {
38
  "op_types": [
39
+ "Sub",
40
+ "Slice",
41
+ "Constant",
42
+ "Identity",
43
+ "Equal",
44
+ "Sigmoid",
45
  "Div",
46
+ "Mul",
47
  "MatMul",
 
 
 
48
  "Pow",
49
+ "Where",
50
+ "Neg",
51
+ "ConstantOfShape",
52
+ "Softmax",
53
  "Add",
54
+ "Sqrt",
55
+ "Unsqueeze",
56
+ "Reshape",
57
  "Expand",
58
+ "ReduceMean",
59
+ "Concat",
60
+ "Less",
61
+ "Cast",
62
  "Gather",
 
63
  "Range",
64
  "Transpose",
65
+ "Shape",
 
66
  "If",
67
+ "Squeeze"
 
 
68
  ],
69
  "weight_type": "QInt8"
70
  },
71
  "decoder_model_merged": {
72
  "op_types": [
73
+ "Sub",
74
+ "Slice",
75
+ "Constant",
76
+ "Identity",
77
+ "Equal",
78
+ "Sigmoid",
79
  "Div",
80
+ "Mul",
81
  "MatMul",
 
 
 
82
  "Pow",
83
+ "Where",
84
+ "Neg",
85
+ "ConstantOfShape",
86
+ "Softmax",
87
  "Add",
88
+ "Sqrt",
89
+ "Unsqueeze",
90
+ "Reshape",
91
  "Expand",
92
+ "ReduceMean",
93
+ "Concat",
94
+ "Less",
95
+ "Cast",
96
  "Gather",
 
97
  "Range",
98
  "Transpose",
99
+ "Shape",
 
100
  "If",
101
+ "Squeeze"
 
 
102
  ],
103
  "weight_type": "QInt8"
104
  }
special_tokens_map.json CHANGED
@@ -1,23 +1,5 @@
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
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
tokenizer_config.json CHANGED
@@ -1,32 +1,38 @@
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
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
  },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
  "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
 
 
 
 
 
 
 
32
  "model_max_length": 2048,
33
  "pad_token": null,
34
  "sp_model_kwargs": {},
35
  "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
37
  "use_default_system_prompt": true
38
  }