Upload folder using huggingface_hub
Browse files- config.json +3 -2
- generation_config.json +1 -1
- onnx/decoder_model_merged.onnx +1 -1
- onnx/decoder_model_merged_quantized.onnx +2 -2
- onnx/decoder_model_quantized.onnx +2 -2
- onnx/decoder_with_past_model_quantized.onnx +2 -2
- quantize_config.json +69 -69
- tokenizer_config.json +2 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -17,8 +17,9 @@
|
|
17 |
"pretraining_tp": 1,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
"rope_scaling": null,
|
|
|
20 |
"tie_word_embeddings": false,
|
21 |
-
"transformers_version": "4.
|
22 |
"use_cache": true,
|
23 |
"vocab_size": 32000
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Xenova/llama2.c-stories42M",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
17 |
"pretraining_tp": 1,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
"rope_scaling": null,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
"tie_word_embeddings": false,
|
22 |
+
"transformers_version": "4.33.0.dev0",
|
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.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.33.0.dev0"
|
6 |
}
|
onnx/decoder_model_merged.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 233913496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:680d2348fa9388e61979d8461735ad105d27e49bedb1601e6b25cd813ac38627
|
3 |
size 233913496
|
onnx/decoder_model_merged_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecebda7e52b45e63820aba9fda9d9b285bff82c73c80f4ae828f3b6fd589e1de
|
3 |
+
size 60022789
|
onnx/decoder_model_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2127d1570779e6856453779104ef0fcf3115d10499e9a3d735cf8192f734c68
|
3 |
+
size 59060350
|
onnx/decoder_with_past_model_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7feaf947dbef1d8a837620946880a29c64fae88b156d62434b785ead3e7c797a
|
3 |
+
size 59062863
|
quantize_config.json
CHANGED
@@ -1,105 +1,105 @@
|
|
1 |
{
|
2 |
-
"per_channel":
|
3 |
-
"reduce_range":
|
4 |
"per_model_config": {
|
5 |
-
"
|
6 |
"op_types": [
|
7 |
-
"
|
8 |
-
"
|
|
|
9 |
"Identity",
|
10 |
-
"
|
11 |
-
"
|
12 |
"Softmax",
|
13 |
-
"
|
14 |
-
"
|
|
|
|
|
|
|
|
|
|
|
15 |
"Constant",
|
16 |
"Range",
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"Cast",
|
20 |
-
"Squeeze",
|
21 |
-
"Unsqueeze",
|
22 |
-
"ConstantOfShape",
|
23 |
-
"Sigmoid",
|
24 |
"Pow",
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
|
|
29 |
"Equal",
|
30 |
-
"Sub",
|
31 |
-
"If",
|
32 |
-
"Shape",
|
33 |
"ReduceMean",
|
34 |
-
"
|
35 |
-
"
|
|
|
36 |
],
|
37 |
"weight_type": "QInt8"
|
38 |
},
|
39 |
-
"
|
40 |
"op_types": [
|
41 |
-
"
|
42 |
-
"
|
|
|
43 |
"Identity",
|
|
|
|
|
|
|
44 |
"MatMul",
|
|
|
|
|
|
|
|
|
|
|
45 |
"Slice",
|
46 |
-
"Softmax",
|
47 |
-
"Sqrt",
|
48 |
-
"Where",
|
49 |
"Constant",
|
50 |
"Range",
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"Cast",
|
54 |
-
"Squeeze",
|
55 |
-
"Unsqueeze",
|
56 |
-
"ConstantOfShape",
|
57 |
-
"Sigmoid",
|
58 |
"Pow",
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
|
|
|
|
62 |
"Equal",
|
63 |
-
"Sub",
|
64 |
-
"If",
|
65 |
-
"Shape",
|
66 |
"ReduceMean",
|
67 |
-
"
|
68 |
-
"
|
|
|
69 |
],
|
70 |
"weight_type": "QInt8"
|
71 |
},
|
72 |
-
"
|
73 |
"op_types": [
|
74 |
-
"
|
75 |
-
"
|
|
|
76 |
"Identity",
|
77 |
-
"
|
78 |
-
"
|
79 |
"Softmax",
|
80 |
-
"
|
81 |
-
"
|
|
|
|
|
|
|
|
|
82 |
"Constant",
|
83 |
"Range",
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"Cast",
|
87 |
-
"Squeeze",
|
88 |
-
"Unsqueeze",
|
89 |
-
"ConstantOfShape",
|
90 |
-
"Sigmoid",
|
91 |
"Pow",
|
92 |
-
"
|
93 |
-
"
|
94 |
-
"
|
95 |
-
"
|
|
|
96 |
"Equal",
|
97 |
-
"Sub",
|
98 |
-
"If",
|
99 |
-
"Shape",
|
100 |
"ReduceMean",
|
101 |
-
"
|
102 |
-
"
|
|
|
103 |
],
|
104 |
"weight_type": "QInt8"
|
105 |
}
|
|
|
1 |
{
|
2 |
+
"per_channel": false,
|
3 |
+
"reduce_range": false,
|
4 |
"per_model_config": {
|
5 |
+
"decoder_model": {
|
6 |
"op_types": [
|
7 |
+
"Unsqueeze",
|
8 |
+
"Concat",
|
9 |
+
"Cast",
|
10 |
"Identity",
|
11 |
+
"Div",
|
12 |
+
"Shape",
|
13 |
"Softmax",
|
14 |
+
"MatMul",
|
15 |
+
"ConstantOfShape",
|
16 |
+
"If",
|
17 |
+
"Add",
|
18 |
+
"Mul",
|
19 |
+
"Less",
|
20 |
+
"Slice",
|
21 |
"Constant",
|
22 |
"Range",
|
23 |
+
"Sub",
|
24 |
+
"Expand",
|
|
|
|
|
|
|
|
|
|
|
25 |
"Pow",
|
26 |
+
"Sigmoid",
|
27 |
+
"Where",
|
28 |
+
"Gather",
|
29 |
+
"Neg",
|
30 |
+
"Squeeze",
|
31 |
"Equal",
|
|
|
|
|
|
|
32 |
"ReduceMean",
|
33 |
+
"Reshape",
|
34 |
+
"Sqrt",
|
35 |
+
"Transpose"
|
36 |
],
|
37 |
"weight_type": "QInt8"
|
38 |
},
|
39 |
+
"decoder_model_merged": {
|
40 |
"op_types": [
|
41 |
+
"Unsqueeze",
|
42 |
+
"Concat",
|
43 |
+
"Cast",
|
44 |
"Identity",
|
45 |
+
"Div",
|
46 |
+
"Shape",
|
47 |
+
"Softmax",
|
48 |
"MatMul",
|
49 |
+
"ConstantOfShape",
|
50 |
+
"If",
|
51 |
+
"Add",
|
52 |
+
"Mul",
|
53 |
+
"Less",
|
54 |
"Slice",
|
|
|
|
|
|
|
55 |
"Constant",
|
56 |
"Range",
|
57 |
+
"Sub",
|
58 |
+
"Expand",
|
|
|
|
|
|
|
|
|
|
|
59 |
"Pow",
|
60 |
+
"Sigmoid",
|
61 |
+
"Where",
|
62 |
+
"Gather",
|
63 |
+
"Neg",
|
64 |
+
"Squeeze",
|
65 |
"Equal",
|
|
|
|
|
|
|
66 |
"ReduceMean",
|
67 |
+
"Reshape",
|
68 |
+
"Sqrt",
|
69 |
+
"Transpose"
|
70 |
],
|
71 |
"weight_type": "QInt8"
|
72 |
},
|
73 |
+
"decoder_with_past_model": {
|
74 |
"op_types": [
|
75 |
+
"Unsqueeze",
|
76 |
+
"Concat",
|
77 |
+
"Cast",
|
78 |
"Identity",
|
79 |
+
"Div",
|
80 |
+
"Shape",
|
81 |
"Softmax",
|
82 |
+
"MatMul",
|
83 |
+
"ConstantOfShape",
|
84 |
+
"If",
|
85 |
+
"Add",
|
86 |
+
"Mul",
|
87 |
+
"Slice",
|
88 |
"Constant",
|
89 |
"Range",
|
90 |
+
"Sub",
|
91 |
+
"Expand",
|
|
|
|
|
|
|
|
|
|
|
92 |
"Pow",
|
93 |
+
"Sigmoid",
|
94 |
+
"Where",
|
95 |
+
"Gather",
|
96 |
+
"Neg",
|
97 |
+
"Squeeze",
|
98 |
"Equal",
|
|
|
|
|
|
|
99 |
"ReduceMean",
|
100 |
+
"Reshape",
|
101 |
+
"Sqrt",
|
102 |
+
"Transpose"
|
103 |
],
|
104 |
"weight_type": "QInt8"
|
105 |
}
|
tokenizer_config.json
CHANGED
@@ -27,5 +27,6 @@
|
|
27 |
"normalized": true,
|
28 |
"rstrip": false,
|
29 |
"single_word": false
|
30 |
-
}
|
|
|
31 |
}
|
|
|
27 |
"normalized": true,
|
28 |
"rstrip": false,
|
29 |
"single_word": false
|
30 |
+
},
|
31 |
+
"use_default_system_prompt": true
|
32 |
}
|