Upload 8 files
Browse files- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- quantize_config.json +97 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "duongna/fooocus_expansion",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"transformers_version": "4.33.2",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50257
|
38 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.33.2"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quantize_config.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": false,
|
3 |
+
"reduce_range": false,
|
4 |
+
"per_model_config": {
|
5 |
+
"decoder_model": {
|
6 |
+
"op_types": [
|
7 |
+
"Constant",
|
8 |
+
"Slice",
|
9 |
+
"Squeeze",
|
10 |
+
"Gather",
|
11 |
+
"Where",
|
12 |
+
"Pow",
|
13 |
+
"Gemm",
|
14 |
+
"Split",
|
15 |
+
"Div",
|
16 |
+
"Add",
|
17 |
+
"ConstantOfShape",
|
18 |
+
"Shape",
|
19 |
+
"Concat",
|
20 |
+
"Sqrt",
|
21 |
+
"Transpose",
|
22 |
+
"Mul",
|
23 |
+
"MatMul",
|
24 |
+
"Tanh",
|
25 |
+
"ReduceMean",
|
26 |
+
"Softmax",
|
27 |
+
"Sub",
|
28 |
+
"Cast",
|
29 |
+
"Reshape",
|
30 |
+
"Range",
|
31 |
+
"Unsqueeze"
|
32 |
+
],
|
33 |
+
"weight_type": "QInt8"
|
34 |
+
},
|
35 |
+
"decoder_model_merged": {
|
36 |
+
"op_types": [
|
37 |
+
"Constant",
|
38 |
+
"Slice",
|
39 |
+
"Squeeze",
|
40 |
+
"Gather",
|
41 |
+
"Where",
|
42 |
+
"Pow",
|
43 |
+
"Gemm",
|
44 |
+
"Add",
|
45 |
+
"Div",
|
46 |
+
"Split",
|
47 |
+
"ConstantOfShape",
|
48 |
+
"Shape",
|
49 |
+
"Concat",
|
50 |
+
"Sqrt",
|
51 |
+
"If",
|
52 |
+
"Transpose",
|
53 |
+
"Mul",
|
54 |
+
"MatMul",
|
55 |
+
"Tanh",
|
56 |
+
"ReduceMean",
|
57 |
+
"Softmax",
|
58 |
+
"Sub",
|
59 |
+
"Cast",
|
60 |
+
"Reshape",
|
61 |
+
"Range",
|
62 |
+
"Unsqueeze"
|
63 |
+
],
|
64 |
+
"weight_type": "QInt8"
|
65 |
+
},
|
66 |
+
"decoder_with_past_model": {
|
67 |
+
"op_types": [
|
68 |
+
"Constant",
|
69 |
+
"Slice",
|
70 |
+
"Squeeze",
|
71 |
+
"Gather",
|
72 |
+
"Where",
|
73 |
+
"Pow",
|
74 |
+
"Gemm",
|
75 |
+
"Split",
|
76 |
+
"Div",
|
77 |
+
"Add",
|
78 |
+
"ConstantOfShape",
|
79 |
+
"Shape",
|
80 |
+
"Concat",
|
81 |
+
"Sqrt",
|
82 |
+
"Transpose",
|
83 |
+
"Mul",
|
84 |
+
"MatMul",
|
85 |
+
"Tanh",
|
86 |
+
"ReduceMean",
|
87 |
+
"Softmax",
|
88 |
+
"Sub",
|
89 |
+
"Cast",
|
90 |
+
"Reshape",
|
91 |
+
"Range",
|
92 |
+
"Unsqueeze"
|
93 |
+
],
|
94 |
+
"weight_type": "QInt8"
|
95 |
+
}
|
96 |
+
}
|
97 |
+
}
|
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": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|