Hugging Face's logo

Xenova
/
llama2.c-stories42M

Text Generation
Transformers.js
PyTorch
ONNX
Transformers
llama
text-generation-inference
Model card Files
xet
Community
4
Xenova HF Staff commited on
Commit
c92f899
·
1 Parent(s): 9db9b7b

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 +57 -56
  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 sha256:2875c864cfa242d3ce797f1c8f47c8779bc4d4d22bedffc7c5220d3405a4b1de
3
- size 167565936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9993acfcd14528ac8bcefc4a6a8bdeddc2e6aada567c8d9e0c601dd0ec603562
3
+ size 167566461
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:315d6c6d96edac7ab954841322d443a69102c059e8ac20ba89faf3f0236769aa
3
- size 168376680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4da7ec2fab9370e45b7e8fbcc1a787e19ad6283aff523b08f9373df9b963849
3
+ size 168377675
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5e81e0464c3028cd88b9f457a8770a16c268258c0fdc290ca04035bdbb575f3
3
- size 43636490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d2095b1db3b264342e0aab8779bdaa311fb3117ae9faddd9e2da26ebd943f8
3
+ size 43637900
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44b2bc266767e042cb7277e7234c916ca678841ccaef3bc1f3e76bfe6c41f689
3
- size 42675110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83784ee0b2b115606e5b69d3d5565e99c826d7aa7e1de5437c12b0a964c28c1d
3
+ size 42675859
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c13e4732ed2e01643955726fa276efa3f3bf49279e42c837ef50893f292b71a
3
- size 167568570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d8434248807a07f0a85468cdbdd138171cb2d48c6b25165b99088821346991
3
+ size 167568998
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:886b10a41ecb479dffa829513765f4e445ddcef1c972d5b95aadd10eecd854df
3
- size 42677756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5689e151084aa2dbf309f6f54f13fea852af91d00ebc2c4f5d9f7e96a39044
3
+ size 42678372
quantize_config.json CHANGED
@@ -5,100 +5,101 @@
5
  "decoder_with_past_model": {
6
  "op_types": [
7
  "Unsqueeze",
8
- "Pow",
9
- "If",
10
- "Gather",
11
- "Constant",
12
- "Squeeze",
13
- "Reshape",
14
- "Slice",
15
  "Neg",
16
- "ConstantOfShape",
17
- "Sigmoid",
18
  "Softmax",
 
19
  "Identity",
20
- "Sub",
21
- "Cast",
22
  "Expand",
23
- "Div",
 
24
  "Mul",
25
- "Add",
26
  "Shape",
27
- "Sqrt",
28
- "Where",
29
- "Equal",
30
  "MatMul",
 
 
 
 
 
 
31
  "Concat",
32
- "Transpose",
33
- "ReduceMean"
 
 
 
 
 
 
34
  ],
35
  "weight_type": "QInt8"
36
  },
37
  "decoder_model": {
38
  "op_types": [
39
  "Unsqueeze",
40
- "Pow",
41
- "If",
42
- "Gather",
43
- "Constant",
44
- "Squeeze",
45
- "Reshape",
46
- "Slice",
47
- "Less",
48
  "Neg",
49
- "ConstantOfShape",
50
- "Sigmoid",
51
  "Softmax",
52
  "Identity",
53
- "Sub",
54
  "Expand",
55
- "Div",
 
56
  "Mul",
57
- "Add",
58
  "Shape",
59
- "Sqrt",
60
- "Where",
61
- "Equal",
62
  "MatMul",
63
- "Concat",
 
64
  "Range",
65
- "Transpose",
 
 
 
 
 
 
 
66
  "Cast",
67
- "ReduceMean"
 
 
68
  ],
69
  "weight_type": "QInt8"
70
  },
71
  "decoder_model_merged": {
72
  "op_types": [
73
  "Unsqueeze",
74
- "Pow",
75
- "If",
76
- "Gather",
77
- "Constant",
78
- "Squeeze",
79
- "Reshape",
80
- "Slice",
81
- "Less",
82
  "Neg",
83
- "ConstantOfShape",
84
- "Sigmoid",
85
  "Softmax",
86
  "Identity",
87
- "Sub",
88
  "Expand",
89
- "Div",
 
90
  "Mul",
91
- "Add",
92
  "Shape",
93
- "Sqrt",
94
- "Where",
95
- "Equal",
96
  "MatMul",
97
- "Concat",
 
98
  "Range",
99
- "Transpose",
 
 
 
 
 
 
 
100
  "Cast",
101
- "ReduceMean"
 
 
102
  ],
103
  "weight_type": "QInt8"
104
  }
 
5
  "decoder_with_past_model": {
6
  "op_types": [
7
  "Unsqueeze",
8
+ "Transpose",
 
 
 
 
 
 
9
  "Neg",
 
 
10
  "Softmax",
11
+ "If",
12
  "Identity",
 
 
13
  "Expand",
14
+ "Where",
15
+ "Constant",
16
  "Mul",
 
17
  "Shape",
18
+ "Sigmoid",
 
 
19
  "MatMul",
20
+ "Div",
21
+ "Squeeze",
22
+ "Range",
23
+ "Sub",
24
+ "Pow",
25
+ "Gather",
26
  "Concat",
27
+ "ReduceMean",
28
+ "ConstantOfShape",
29
+ "Reshape",
30
+ "Sqrt",
31
+ "Cast",
32
+ "Slice",
33
+ "Add",
34
+ "Equal"
35
  ],
36
  "weight_type": "QInt8"
37
  },
38
  "decoder_model": {
39
  "op_types": [
40
  "Unsqueeze",
41
+ "Transpose",
 
 
 
 
 
 
 
42
  "Neg",
43
+ "Less",
44
+ "If",
45
  "Softmax",
46
  "Identity",
 
47
  "Expand",
48
+ "Where",
49
+ "Constant",
50
  "Mul",
 
51
  "Shape",
52
+ "Sigmoid",
 
 
53
  "MatMul",
54
+ "Div",
55
+ "Squeeze",
56
  "Range",
57
+ "Sub",
58
+ "Pow",
59
+ "Gather",
60
+ "Concat",
61
+ "ReduceMean",
62
+ "ConstantOfShape",
63
+ "Reshape",
64
+ "Slice",
65
  "Cast",
66
+ "Sqrt",
67
+ "Add",
68
+ "Equal"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_model_merged": {
73
  "op_types": [
74
  "Unsqueeze",
75
+ "Transpose",
 
 
 
 
 
 
 
76
  "Neg",
77
+ "Less",
78
+ "If",
79
  "Softmax",
80
  "Identity",
 
81
  "Expand",
82
+ "Where",
83
+ "Constant",
84
  "Mul",
 
85
  "Shape",
86
+ "Sigmoid",
 
 
87
  "MatMul",
88
+ "Div",
89
+ "Squeeze",
90
  "Range",
91
+ "Sub",
92
+ "Pow",
93
+ "Gather",
94
+ "Concat",
95
+ "ReduceMean",
96
+ "ConstantOfShape",
97
+ "Reshape",
98
+ "Slice",
99
  "Cast",
100
+ "Sqrt",
101
+ "Add",
102
+ "Equal"
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
  ],