Hugging Face's logo

Xenova
/
llama2.c-stories15M

Text Generation
Transformers.js
PyTorch
ONNX
Transformers
llama
Model card Files Community
2
Xenova HF staff commited on
Commit
08c64db
•
1 Parent(s): 450486d

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 +64 -65
  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-stories15M",
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:ff5e861cc2ac67ff2ded19ed940b2507ed708612608295fcbf6ecafde8292a0a
3
- size 97945098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07c49d31f79ac42c3a06e3cf179bc990a38b2ce20b267ebaba22b65bda1c930
3
+ size 61080662
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e62780167c73c2596c4a08ff748ce3f3e33fcca0e27e9ba7d83dcbd9c8d5516
3
- size 98260154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a203087bb867a9d6065e9504295746b12b01ad4dec0c998d54a237b72b24626
3
+ size 61395360
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccbf01448c56bf2a96dc640fe8f4a2b018bfea69365a2a972a172144dad400d4
3
- size 25279161
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c6fd050e162abbe2147013e1a833c95cc72c9c590297ee904673eb30e2cbac
3
+ size 16060883
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fef635548a485428acac2ce40c5de6491a9d73dc2e1192a5a127fd55cd492a4
3
- size 24849487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a6615f6643b27e8c0716db156d04c4871848dc8d6696287bfb7581394cbf58
3
+ size 15632262
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83172a6c980948c016f78262097ffa2443c7e4e02ab45b7661bbff65b0886090
3
- size 97945415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01baac7ecd5ecd77ac19098379c6dcce3586aec302667c03ab015ef5155457ad
3
+ size 61081070
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49d37b90c7c768529f9c643a0543c5bf7d9890f4b1e5c860060ba861beec5e67
3
- size 24849120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b4aed183fe25e825107c79d38bb1e05724b5763c55f5eaa2b2b5a1989f70d4
3
+ size 15632019
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
- "Range",
8
- "Reshape",
 
9
  "Pow",
10
- "Div",
11
- "Add",
 
 
 
 
12
  "ReduceMean",
13
- "If",
14
- "Sigmoid",
15
- "Less",
16
  "Sqrt",
17
- "Squeeze",
18
- "Gather",
19
- "Constant",
20
  "Slice",
21
- "Shape",
 
 
 
 
 
 
 
 
22
  "Identity",
23
  "Neg",
24
  "Transpose",
25
- "Where",
26
- "Softmax",
27
- "Unsqueeze",
28
- "Expand",
29
- "Equal",
30
- "Cast",
31
- "Concat",
32
- "Mul",
33
- "Sub",
34
- "ConstantOfShape",
35
- "MatMul"
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
- "decoder_with_past_model": {
40
  "op_types": [
 
 
 
 
 
 
41
  "Range",
 
42
  "Reshape",
43
- "Pow",
44
- "Div",
45
- "Add",
46
  "ReduceMean",
47
- "If",
48
- "Sigmoid",
49
  "Sqrt",
50
- "Squeeze",
51
- "Gather",
52
- "Constant",
53
  "Slice",
54
- "Shape",
 
 
 
 
 
 
 
 
 
55
  "Identity",
56
  "Neg",
57
  "Transpose",
58
- "Where",
59
- "Softmax",
60
- "Unsqueeze",
61
- "Expand",
62
- "Equal",
63
- "Cast",
64
- "Concat",
65
- "Mul",
66
- "Sub",
67
- "ConstantOfShape",
68
- "MatMul"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_model_merged": {
73
  "op_types": [
 
 
 
 
 
 
74
  "Range",
 
75
  "Reshape",
76
- "Pow",
77
- "Div",
78
- "Add",
79
  "ReduceMean",
80
- "If",
81
- "Sigmoid",
82
- "Less",
83
  "Sqrt",
84
- "Squeeze",
85
- "Gather",
86
- "Constant",
87
  "Slice",
88
- "Shape",
 
 
 
 
 
 
 
 
 
89
  "Identity",
90
  "Neg",
91
  "Transpose",
92
- "Where",
93
- "Softmax",
94
- "Unsqueeze",
95
- "Expand",
96
- "Equal",
97
- "Cast",
98
- "Concat",
99
- "Mul",
100
- "Sub",
101
- "ConstantOfShape",
102
- "MatMul"
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
+ "Unsqueeze",
8
+ "ConstantOfShape",
9
+ "Shape",
10
  "Pow",
11
+ "Expand",
12
+ "Concat",
13
+ "Cast",
14
+ "Reshape",
15
+ "Softmax",
16
+ "Where",
17
  "ReduceMean",
18
+ "Mul",
 
 
19
  "Sqrt",
 
 
 
20
  "Slice",
21
+ "Constant",
22
+ "If",
23
+ "Gather",
24
+ "Equal",
25
+ "Div",
26
+ "MatMul",
27
+ "Squeeze",
28
+ "Sigmoid",
29
+ "Add",
30
  "Identity",
31
  "Neg",
32
  "Transpose",
33
+ "Sub"
 
 
 
 
 
 
 
 
 
 
34
  ],
35
  "weight_type": "QInt8"
36
  },
37
+ "decoder_model": {
38
  "op_types": [
39
+ "Unsqueeze",
40
+ "ConstantOfShape",
41
+ "Shape",
42
+ "Pow",
43
+ "Expand",
44
+ "Concat",
45
  "Range",
46
+ "Cast",
47
  "Reshape",
48
+ "Softmax",
49
+ "Where",
 
50
  "ReduceMean",
51
+ "Mul",
 
52
  "Sqrt",
 
 
 
53
  "Slice",
54
+ "Less",
55
+ "Constant",
56
+ "If",
57
+ "Gather",
58
+ "Equal",
59
+ "Div",
60
+ "MatMul",
61
+ "Squeeze",
62
+ "Sigmoid",
63
+ "Add",
64
  "Identity",
65
  "Neg",
66
  "Transpose",
67
+ "Sub"
 
 
 
 
 
 
 
 
 
 
68
  ],
69
  "weight_type": "QInt8"
70
  },
71
  "decoder_model_merged": {
72
  "op_types": [
73
+ "Unsqueeze",
74
+ "ConstantOfShape",
75
+ "Shape",
76
+ "Pow",
77
+ "Expand",
78
+ "Concat",
79
  "Range",
80
+ "Cast",
81
  "Reshape",
82
+ "Softmax",
83
+ "Where",
 
84
  "ReduceMean",
85
+ "Mul",
 
 
86
  "Sqrt",
 
 
 
87
  "Slice",
88
+ "Less",
89
+ "Constant",
90
+ "If",
91
+ "Gather",
92
+ "Equal",
93
+ "Div",
94
+ "MatMul",
95
+ "Squeeze",
96
+ "Sigmoid",
97
+ "Add",
98
  "Identity",
99
  "Neg",
100
  "Transpose",
101
+ "Sub"
 
 
 
 
 
 
 
 
 
 
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
  }