Upload folder using huggingface_hub
Browse files- added_tokens.json +40 -0
- config.json +27 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged_quantized.onnx +3 -0
- onnx/decoder_model_quantized.onnx +3 -0
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/decoder_with_past_model_quantized.onnx +3 -0
- quantize_config.json +127 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257
|
40 |
+
}
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TabbyML/J-350M",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTJForCausalLM"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"embd_pdrop": 0.0,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gptj",
|
14 |
+
"n_embd": 1024,
|
15 |
+
"n_head": 16,
|
16 |
+
"n_inner": null,
|
17 |
+
"n_layer": 20,
|
18 |
+
"n_positions": 2048,
|
19 |
+
"resid_pdrop": 0.0,
|
20 |
+
"rotary_dim": 32,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"tokenizer_class": "CodeGenTokenizer",
|
24 |
+
"transformers_version": "4.33.0.dev0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 51200
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.33.0.dev0"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
onnx/decoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:152e8ee7cf9635250dc1d59f82fa83d785a004dbaaf41b201ac3d171b6039315
|
3 |
+
size 1431962198
|
onnx/decoder_model_merged.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9be275093bf50d50f65d22a9e82e672d6d59c53884864dd008dc4bd906b15efe
|
3 |
+
size 1437087087
|
onnx/decoder_model_merged_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf9bf08f05595f85aa8edd51c15a75546db814ab27c1235638c382a191e9241c
|
3 |
+
size 368247320
|
onnx/decoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cb66ee755aca706c867d0aef62cdef3f34aa78ab87686414a87aa05c02d2e68
|
3 |
+
size 362768959
|
onnx/decoder_with_past_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6639bcd8f4b0301ed3717d3ac71379e1cdacb87d4475cfe91bcf042a2c6759a
|
3 |
+
size 1431973333
|
onnx/decoder_with_past_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1487d046f74b9cf2d3dddb0caac1b1497b83028afedad63e43dabf7a3f718b6c
|
3 |
+
size 362782475
|
quantize_config.json
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": false,
|
3 |
+
"reduce_range": false,
|
4 |
+
"per_model_config": {
|
5 |
+
"decoder_model": {
|
6 |
+
"op_types": [
|
7 |
+
"Sub",
|
8 |
+
"Constant",
|
9 |
+
"Shape",
|
10 |
+
"Transpose",
|
11 |
+
"SequenceInsert",
|
12 |
+
"Tanh",
|
13 |
+
"Softmax",
|
14 |
+
"MatMul",
|
15 |
+
"SequenceAt",
|
16 |
+
"SplitToSequence",
|
17 |
+
"GatherElements",
|
18 |
+
"Loop",
|
19 |
+
"Tile",
|
20 |
+
"Squeeze",
|
21 |
+
"Cast",
|
22 |
+
"Concat",
|
23 |
+
"Mul",
|
24 |
+
"ReduceMean",
|
25 |
+
"ConstantOfShape",
|
26 |
+
"SequenceEmpty",
|
27 |
+
"Expand",
|
28 |
+
"Unsqueeze",
|
29 |
+
"Neg",
|
30 |
+
"Sqrt",
|
31 |
+
"Split",
|
32 |
+
"Slice",
|
33 |
+
"Range",
|
34 |
+
"Equal",
|
35 |
+
"Div",
|
36 |
+
"ConcatFromSequence",
|
37 |
+
"Gather",
|
38 |
+
"Reshape",
|
39 |
+
"Pow",
|
40 |
+
"Where",
|
41 |
+
"Add"
|
42 |
+
],
|
43 |
+
"weight_type": "QInt8"
|
44 |
+
},
|
45 |
+
"decoder_model_merged": {
|
46 |
+
"op_types": [
|
47 |
+
"Sub",
|
48 |
+
"Constant",
|
49 |
+
"Shape",
|
50 |
+
"Transpose",
|
51 |
+
"SequenceInsert",
|
52 |
+
"Tanh",
|
53 |
+
"Softmax",
|
54 |
+
"MatMul",
|
55 |
+
"SequenceAt",
|
56 |
+
"SplitToSequence",
|
57 |
+
"GatherElements",
|
58 |
+
"Loop",
|
59 |
+
"Tile",
|
60 |
+
"Squeeze",
|
61 |
+
"Cast",
|
62 |
+
"Concat",
|
63 |
+
"If",
|
64 |
+
"Mul",
|
65 |
+
"ReduceMean",
|
66 |
+
"ConstantOfShape",
|
67 |
+
"SequenceEmpty",
|
68 |
+
"Expand",
|
69 |
+
"Unsqueeze",
|
70 |
+
"Neg",
|
71 |
+
"Sqrt",
|
72 |
+
"Split",
|
73 |
+
"Slice",
|
74 |
+
"Range",
|
75 |
+
"Equal",
|
76 |
+
"Div",
|
77 |
+
"ConcatFromSequence",
|
78 |
+
"Gather",
|
79 |
+
"Reshape",
|
80 |
+
"Pow",
|
81 |
+
"Where",
|
82 |
+
"Add"
|
83 |
+
],
|
84 |
+
"weight_type": "QInt8"
|
85 |
+
},
|
86 |
+
"decoder_with_past_model": {
|
87 |
+
"op_types": [
|
88 |
+
"Sub",
|
89 |
+
"Constant",
|
90 |
+
"Shape",
|
91 |
+
"Transpose",
|
92 |
+
"SequenceInsert",
|
93 |
+
"Tanh",
|
94 |
+
"Softmax",
|
95 |
+
"MatMul",
|
96 |
+
"SequenceAt",
|
97 |
+
"SplitToSequence",
|
98 |
+
"GatherElements",
|
99 |
+
"Loop",
|
100 |
+
"Tile",
|
101 |
+
"Cast",
|
102 |
+
"Squeeze",
|
103 |
+
"Concat",
|
104 |
+
"Mul",
|
105 |
+
"ReduceMean",
|
106 |
+
"ConstantOfShape",
|
107 |
+
"SequenceEmpty",
|
108 |
+
"Expand",
|
109 |
+
"Unsqueeze",
|
110 |
+
"Neg",
|
111 |
+
"Sqrt",
|
112 |
+
"Split",
|
113 |
+
"Slice",
|
114 |
+
"Range",
|
115 |
+
"Equal",
|
116 |
+
"Div",
|
117 |
+
"ConcatFromSequence",
|
118 |
+
"Gather",
|
119 |
+
"Reshape",
|
120 |
+
"Pow",
|
121 |
+
"Where",
|
122 |
+
"Add"
|
123 |
+
],
|
124 |
+
"weight_type": "QInt8"
|
125 |
+
}
|
126 |
+
}
|
127 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"tokenizer_class": "CodeGenTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|