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
196fd4d
·
1 Parent(s): d1ebbd6

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +1 -0
  2. generation_config.json +1 -1
  3. onnx/decoder_model.onnx +1 -1
  4. onnx/decoder_model_merged.onnx +1 -1
  5. onnx/decoder_model_merged_quantized.onnx +1 -1
  6. onnx/decoder_model_quantized.onnx +1 -1
  7. onnx/decoder_with_past_model.onnx +1 -1
  8. onnx/decoder_with_past_model_quantized.onnx +1 -1
  9. quantize_config.json +64 -64
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
  ],
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": "4.33.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fff8a7fe61ffdacec9bfdc7f045bc60ee240c46d63e0c671dabab2a21944c46
3
  size 97945098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5e861cc2ac67ff2ded19ed940b2507ed708612608295fcbf6ecafde8292a0a
3
  size 97945098
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6816b265a96d80bb85a622c394dc819b269680f327b82ea64f3c77f32117d84e
3
  size 98260154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e62780167c73c2596c4a08ff748ce3f3e33fcca0e27e9ba7d83dcbd9c8d5516
3
  size 98260154
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:473abf17f5284a881ea1086cfead870211b933365a91cead05e2274f94b7d5cb
3
  size 25279161
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbf01448c56bf2a96dc640fe8f4a2b018bfea69365a2a972a172144dad400d4
3
  size 25279161
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c62704973668509b573854d3c24d3d47322db722538f0ce6064bc9f425802e
3
  size 24849487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fef635548a485428acac2ce40c5de6491a9d73dc2e1192a5a127fd55cd492a4
3
  size 24849487
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62dc5b8e6580e7fff028c5bc2993598be53b0d8b28401206a648f3b75517bce8
3
  size 97945415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83172a6c980948c016f78262097ffa2443c7e4e02ab45b7661bbff65b0886090
3
  size 97945415
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dafb7a1a57c760eac3203352c6db49456532166dca7ff046bdb5b7127d3eadec
3
  size 24849120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d37b90c7c768529f9c643a0543c5bf7d9890f4b1e5c860060ba861beec5e67
3
  size 24849120
quantize_config.json CHANGED
@@ -4,102 +4,102 @@
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
7
- "Squeeze",
8
- "Identity",
9
- "Constant",
10
- "Add",
11
  "Pow",
12
- "ConstantOfShape",
 
 
13
  "If",
14
- "Reshape",
15
- "Sqrt",
16
- "Equal",
17
- "Where",
18
  "Sigmoid",
19
- "Sub",
20
- "ReduceMean",
21
- "Transpose",
 
 
22
  "Slice",
 
 
23
  "Neg",
 
 
24
  "Softmax",
25
- "Range",
26
- "Shape",
27
- "Div",
28
- "Gather",
29
- "Concat",
30
  "Expand",
 
31
  "Cast",
32
- "Less",
33
- "Unsqueeze",
34
- "MatMul",
35
- "Mul"
 
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
- "decoder_model_merged": {
40
  "op_types": [
41
- "Squeeze",
42
- "Identity",
43
- "Constant",
44
- "Add",
45
  "Pow",
46
- "ConstantOfShape",
 
 
47
  "If",
48
- "Reshape",
49
- "Sqrt",
50
- "Equal",
51
- "Where",
52
  "Sigmoid",
53
- "Sub",
54
- "ReduceMean",
55
- "Transpose",
 
56
  "Slice",
 
 
57
  "Neg",
 
 
58
  "Softmax",
59
- "Range",
60
- "Shape",
61
- "Div",
62
- "Gather",
63
- "Concat",
64
  "Expand",
 
65
  "Cast",
66
- "Less",
67
- "Unsqueeze",
68
- "MatMul",
69
- "Mul"
 
70
  ],
71
  "weight_type": "QInt8"
72
  },
73
- "decoder_with_past_model": {
74
  "op_types": [
75
- "Squeeze",
76
- "Identity",
77
- "Constant",
78
- "Add",
79
  "Pow",
80
- "ConstantOfShape",
 
 
81
  "If",
82
- "Reshape",
83
- "Sqrt",
84
- "Where",
85
- "Equal",
86
  "Sigmoid",
87
- "Sub",
88
- "ReduceMean",
89
- "Transpose",
 
 
90
  "Slice",
 
 
91
  "Neg",
 
 
92
  "Softmax",
93
- "Range",
94
- "Shape",
95
- "Div",
96
- "Gather",
97
- "Concat",
98
  "Expand",
 
99
  "Cast",
100
- "Unsqueeze",
101
- "MatMul",
102
- "Mul"
 
 
103
  ],
104
  "weight_type": "QInt8"
105
  }
 
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
  }