new-files
#1
by
kazssym
- opened
- .gitattributes +0 -3
- .gitignore +0 -1
- README.md +0 -13
- config.json +0 -28
- model.onnx +0 -3
- model.onnx_data +0 -3
- special_tokens_map.json +0 -23
- tokenizer.json +0 -0
- tokenizer_config.json +0 -211
.gitattributes
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
-
* text=auto
|
2 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
3 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
4 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
@@ -15,7 +14,6 @@
|
|
15 |
*.npy filter=lfs diff=lfs merge=lfs -text
|
16 |
*.npz filter=lfs diff=lfs merge=lfs -text
|
17 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.onnx_data filter=lfs diff=lfs merge=lfs -text
|
19 |
*.onnx.data filter=lfs diff=lfs merge=lfs -text
|
20 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
21 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
@@ -36,4 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
36 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
37 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
38 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
39 |
-
model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
14 |
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
17 |
*.onnx.data filter=lfs diff=lfs merge=lfs -text
|
18 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
19 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
|
|
34 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
35 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
36 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
.gitignore
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
.venv
|
|
|
|
README.md
CHANGED
@@ -1,16 +1,3 @@
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
-
tags:
|
4 |
-
- causal-lm
|
5 |
---
|
6 |
-
# Description
|
7 |
-
|
8 |
-
This is a float16 ONNX model for [our test scripts](https://github.com/kazssym/stablelm-study-2).
|
9 |
-
It was exported from [stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) to ONNX with a [modified version](https://github.com/huggingface/optimum/pull/1719) of Hugging Face Optimum.
|
10 |
-
It is quite possible to have problems.
|
11 |
-
|
12 |
-
# Exporting
|
13 |
-
|
14 |
-
This model was exported with [our test scripts](https://github.com/kazssym/stablelm-study-2).
|
15 |
-
|
16 |
-
The source model requires [Transformers](https://github.com/huggingface/transformers) 4.38 or later to export.
|
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
@@ -1,28 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "./exported-intermediate\\config.json",
|
3 |
-
"architectures": [
|
4 |
-
"StableLmForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"eos_token_id": 0,
|
9 |
-
"hidden_act": "silu",
|
10 |
-
"hidden_dropout": 0.0,
|
11 |
-
"hidden_size": 2560,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 6912,
|
14 |
-
"layer_norm_eps": 1e-05,
|
15 |
-
"max_position_embeddings": 4096,
|
16 |
-
"model_type": "stablelm",
|
17 |
-
"num_attention_heads": 32,
|
18 |
-
"num_hidden_layers": 32,
|
19 |
-
"num_key_value_heads": 32,
|
20 |
-
"partial_rotary_factor": 0.25,
|
21 |
-
"rope_scaling": null,
|
22 |
-
"rope_theta": 10000,
|
23 |
-
"tie_word_embeddings": false,
|
24 |
-
"transformers_version": "4.38.2",
|
25 |
-
"use_cache": true,
|
26 |
-
"use_qkv_bias": false,
|
27 |
-
"vocab_size": 50304
|
28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.onnx
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:4bbe1ceef5fd5feb62fcfc965b5a1e0a359e0cdccd22f467458856a554688045
|
3 |
-
size 1483373
|
|
|
|
|
|
|
|
model.onnx_data
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:dfdfdfff1b64b0c453d00a8450ec34ff09b15c3ff609a82d91c7ade7bed75bc1
|
3 |
-
size 5590886400
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1,23 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
DELETED
@@ -1,211 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"0": {
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"1": {
|
13 |
-
"content": "<|padding|>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"50254": {
|
21 |
-
"content": " ",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": true,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": false
|
27 |
-
},
|
28 |
-
"50255": {
|
29 |
-
"content": " ",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": false
|
35 |
-
},
|
36 |
-
"50256": {
|
37 |
-
"content": " ",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": false
|
43 |
-
},
|
44 |
-
"50257": {
|
45 |
-
"content": " ",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": false
|
51 |
-
},
|
52 |
-
"50258": {
|
53 |
-
"content": " ",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": true,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": false
|
59 |
-
},
|
60 |
-
"50259": {
|
61 |
-
"content": " ",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": true,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": false
|
67 |
-
},
|
68 |
-
"50260": {
|
69 |
-
"content": " ",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": true,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": false
|
75 |
-
},
|
76 |
-
"50261": {
|
77 |
-
"content": " ",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": true,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": false
|
83 |
-
},
|
84 |
-
"50262": {
|
85 |
-
"content": " ",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": true,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": false
|
91 |
-
},
|
92 |
-
"50263": {
|
93 |
-
"content": " ",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": true,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": false
|
99 |
-
},
|
100 |
-
"50264": {
|
101 |
-
"content": " ",
|
102 |
-
"lstrip": false,
|
103 |
-
"normalized": true,
|
104 |
-
"rstrip": false,
|
105 |
-
"single_word": false,
|
106 |
-
"special": false
|
107 |
-
},
|
108 |
-
"50265": {
|
109 |
-
"content": " ",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": true,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false,
|
114 |
-
"special": false
|
115 |
-
},
|
116 |
-
"50266": {
|
117 |
-
"content": " ",
|
118 |
-
"lstrip": false,
|
119 |
-
"normalized": true,
|
120 |
-
"rstrip": false,
|
121 |
-
"single_word": false,
|
122 |
-
"special": false
|
123 |
-
},
|
124 |
-
"50267": {
|
125 |
-
"content": " ",
|
126 |
-
"lstrip": false,
|
127 |
-
"normalized": true,
|
128 |
-
"rstrip": false,
|
129 |
-
"single_word": false,
|
130 |
-
"special": false
|
131 |
-
},
|
132 |
-
"50268": {
|
133 |
-
"content": " ",
|
134 |
-
"lstrip": false,
|
135 |
-
"normalized": true,
|
136 |
-
"rstrip": false,
|
137 |
-
"single_word": false,
|
138 |
-
"special": false
|
139 |
-
},
|
140 |
-
"50269": {
|
141 |
-
"content": " ",
|
142 |
-
"lstrip": false,
|
143 |
-
"normalized": true,
|
144 |
-
"rstrip": false,
|
145 |
-
"single_word": false,
|
146 |
-
"special": false
|
147 |
-
},
|
148 |
-
"50270": {
|
149 |
-
"content": " ",
|
150 |
-
"lstrip": false,
|
151 |
-
"normalized": true,
|
152 |
-
"rstrip": false,
|
153 |
-
"single_word": false,
|
154 |
-
"special": false
|
155 |
-
},
|
156 |
-
"50271": {
|
157 |
-
"content": " ",
|
158 |
-
"lstrip": false,
|
159 |
-
"normalized": true,
|
160 |
-
"rstrip": false,
|
161 |
-
"single_word": false,
|
162 |
-
"special": false
|
163 |
-
},
|
164 |
-
"50272": {
|
165 |
-
"content": " ",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": true,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false,
|
170 |
-
"special": false
|
171 |
-
},
|
172 |
-
"50273": {
|
173 |
-
"content": " ",
|
174 |
-
"lstrip": false,
|
175 |
-
"normalized": true,
|
176 |
-
"rstrip": false,
|
177 |
-
"single_word": false,
|
178 |
-
"special": false
|
179 |
-
},
|
180 |
-
"50274": {
|
181 |
-
"content": " ",
|
182 |
-
"lstrip": false,
|
183 |
-
"normalized": true,
|
184 |
-
"rstrip": false,
|
185 |
-
"single_word": false,
|
186 |
-
"special": false
|
187 |
-
},
|
188 |
-
"50275": {
|
189 |
-
"content": " ",
|
190 |
-
"lstrip": false,
|
191 |
-
"normalized": true,
|
192 |
-
"rstrip": false,
|
193 |
-
"single_word": false,
|
194 |
-
"special": false
|
195 |
-
},
|
196 |
-
"50276": {
|
197 |
-
"content": " ",
|
198 |
-
"lstrip": false,
|
199 |
-
"normalized": true,
|
200 |
-
"rstrip": false,
|
201 |
-
"single_word": false,
|
202 |
-
"special": false
|
203 |
-
}
|
204 |
-
},
|
205 |
-
"bos_token": "<|endoftext|>",
|
206 |
-
"clean_up_tokenization_spaces": true,
|
207 |
-
"eos_token": "<|endoftext|>",
|
208 |
-
"model_max_length": 1000000000000000019884624838656,
|
209 |
-
"tokenizer_class": "GPTNeoXTokenizer",
|
210 |
-
"unk_token": "<|endoftext|>"
|
211 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|