Hugging Face's logo

Xenova
/
llama2.c-stories15M

Text Generation
Transformers.js
PyTorch
ONNX
Safetensors
Transformers
llama
text-generation-inference
Model card Files
xet
Community
5
Xenova HF Staff commited on
Commit
cab1df3
·
1 Parent(s): 08c64db

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +1 -1
  2. generation_config.json +1 -1
  3. onnx/decoder_model.onnx +2 -2
  4. onnx/decoder_model_merged.onnx +2 -2
  5. onnx/decoder_model_merged_quantized.onnx +2 -2
  6. onnx/decoder_model_quantized.onnx +2 -2
  7. onnx/decoder_with_past_model.onnx +2 -2
  8. onnx/decoder_with_past_model_quantized.onnx +2 -2
  9. quantize_config.json +59 -58
  10. tokenizer.json +3 -3
config.json CHANGED
@@ -19,7 +19,7 @@
19
  "rope_scaling": null,
20
  "rope_theta": 10000.0,
21
  "tie_word_embeddings": true,
22
- "transformers_version": "4.34.0.dev0",
23
  "use_cache": true,
24
  "vocab_size": 32000
25
  }
 
19
  "rope_scaling": null,
20
  "rope_theta": 10000.0,
21
  "tie_word_embeddings": true,
22
+ "transformers_version": "4.33.2",
23
  "use_cache": true,
24
  "vocab_size": 32000
25
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.34.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.33.2"
6
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d07c49d31f79ac42c3a06e3cf179bc990a38b2ce20b267ebaba22b65bda1c930
3
- size 61080662
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f70897713a4dbec69d11448e3f981430ab718c4a289f4de80f658464f2659a
3
+ size 61081173
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a203087bb867a9d6065e9504295746b12b01ad4dec0c998d54a237b72b24626
3
- size 61395360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c7c6335d1223f6ab9487a4188f9a5e23de6b69cc4818abce74ae739b78e0a3
3
+ size 61396333
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32c6fd050e162abbe2147013e1a833c95cc72c9c590297ee904673eb30e2cbac
3
- size 16060883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4c17b1603aabf0a74add6342a78f7a1ed185bef48d1ce7abac3addd474841d
3
+ size 16062272
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1a6615f6643b27e8c0716db156d04c4871848dc8d6696287bfb7581394cbf58
3
- size 15632262
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4148360eac0d7cc2285fa1224549d0e6785154e85308cb4b6ded718079ffcf
3
+ size 15632996
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01baac7ecd5ecd77ac19098379c6dcce3586aec302667c03ab015ef5155457ad
3
- size 61081070
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca95d9a38f64a2be3c7059fd5f1b05b7ff7d50ada2b054accacb1017187332f
3
+ size 61081490
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42b4aed183fe25e825107c79d38bb1e05724b5763c55f5eaa2b2b5a1989f70d4
3
- size 15632019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444b3b1b8d53362b5c1c082636a9add56766d8d9f7ad58638ec11a42911825f0
3
+ size 15632629
quantize_config.json CHANGED
@@ -4,101 +4,102 @@
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
  }
 
4
  "per_model_config": {
5
  "decoder_with_past_model": {
6
  "op_types": [
7
+ "Neg",
 
 
8
  "Pow",
9
+ "Identity",
 
10
  "Cast",
11
+ "Add",
12
  "Softmax",
13
+ "Reshape",
14
+ "Squeeze",
15
  "ReduceMean",
16
+ "Shape",
17
+ "Where",
18
+ "Equal",
19
+ "Sigmoid",
20
  "Sqrt",
 
21
  "Constant",
22
+ "Mul",
23
  "If",
24
+ "ConstantOfShape",
25
+ "Unsqueeze",
26
+ "Concat",
27
+ "Expand",
28
+ "Sub",
29
  "MatMul",
30
+ "Gather",
31
+ "Range",
 
 
 
32
  "Transpose",
33
+ "Slice",
34
+ "Div"
35
  ],
36
  "weight_type": "QInt8"
37
  },
38
  "decoder_model": {
39
  "op_types": [
40
+ "Less",
 
 
41
  "Pow",
42
+ "Neg",
43
+ "Identity",
 
44
  "Cast",
45
+ "Add",
46
  "Softmax",
47
+ "Reshape",
48
+ "Squeeze",
49
  "ReduceMean",
50
+ "Shape",
51
+ "Where",
52
+ "Equal",
53
+ "Sigmoid",
54
  "Sqrt",
 
 
55
  "Constant",
56
+ "Mul",
57
  "If",
58
+ "ConstantOfShape",
59
+ "Unsqueeze",
60
+ "Concat",
61
+ "Expand",
62
+ "Sub",
63
  "MatMul",
64
+ "Range",
65
+ "Gather",
 
 
 
66
  "Transpose",
67
+ "Slice",
68
+ "Div"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_model_merged": {
73
  "op_types": [
74
+ "Less",
 
 
75
  "Pow",
76
+ "Neg",
77
+ "Identity",
 
78
  "Cast",
79
+ "Add",
80
  "Softmax",
81
+ "Reshape",
82
+ "Squeeze",
83
  "ReduceMean",
84
+ "Shape",
85
+ "Where",
86
+ "Equal",
87
+ "Sigmoid",
88
  "Sqrt",
 
 
89
  "Constant",
90
+ "Mul",
91
  "If",
92
+ "ConstantOfShape",
93
+ "Unsqueeze",
94
+ "Concat",
95
+ "Expand",
96
+ "Sub",
97
  "MatMul",
98
+ "Gather",
99
+ "Range",
 
 
 
100
  "Transpose",
101
+ "Slice",
102
+ "Div"
103
  ],
104
  "weight_type": "QInt8"
105
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -27,7 +27,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": true,
31
  "special": true
32
  }
33
  ],
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
32
  }
33
  ],