Hugging Face's logo

deepseek-ai
/
deepseek-coder-1.3b-instruct

Text Generation
Transformers
PyTorch
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
 Community
11

Adding ONNX file of this model

#4
by actcentive - opened
base: refs/heads/main
←
from: refs/pr/4
Discussion Files changed
+64355
-0
Files changed (16) hide show
  1. .gitattributes +7 -0
  2. onnx/Constant_106_attr__value +3 -0
  3. onnx/Constant_114_attr__value +3 -0
  4. onnx/Constant_162_attr__value +3 -0
  5. onnx/Constant_170_attr__value +3 -0
  6. onnx/config.json +29 -0
  7. onnx/decoder_model.onnx +3 -0
  8. onnx/decoder_model.onnx_data +3 -0
  9. onnx/decoder_model_merged.onnx +3 -0
  10. onnx/decoder_model_merged.onnx_data +3 -0
  11. onnx/decoder_with_past_model.onnx +3 -0
  12. onnx/decoder_with_past_model.onnx_data +3 -0
  13. onnx/generation_config.json +6 -0
  14. onnx/special_tokens_map.json +5 -0
  15. onnx/tokenizer.json +0 -0
  16. onnx/tokenizer_config.json +192 -0
.gitattributes CHANGED
@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/Constant_162_attr__value filter=lfs diff=lfs merge=lfs -text
37
+ onnx/Constant_170_attr__value filter=lfs diff=lfs merge=lfs -text
38
+ onnx/Constant_106_attr__value filter=lfs diff=lfs merge=lfs -text
39
+ onnx/Constant_114_attr__value filter=lfs diff=lfs merge=lfs -text
40
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
41
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
42
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
onnx/Constant_106_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea4e41a2509d22f53eb99aacf35d86ae1ead1d35ed67e375f6ffc877466d365
3
+ size 8388608
onnx/Constant_114_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8e22ba3993ca0cb711fcb78000c7e3f0e0226b2bb6717f56441abe5d6faf8e
3
+ size 8388608
onnx/Constant_162_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea4e41a2509d22f53eb99aacf35d86ae1ead1d35ed67e375f6ffc877466d365
3
+ size 8388608
onnx/Constant_170_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8e22ba3993ca0cb711fcb78000c7e3f0e0226b2bb6717f56441abe5d6faf8e
3
+ size 8388608
onnx/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 32013,
8
+ "eos_token_id": 32021,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 5504,
13
+ "max_position_embeddings": 16384,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 16,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "factor": 4.0,
22
+ "type": "linear"
23
+ },
24
+ "rope_theta": 100000,
25
+ "tie_word_embeddings": false,
26
+ "transformers_version": "4.34.0",
27
+ "use_cache": true,
28
+ "vocab_size": 32256
29
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65bf40cc582a11825d92374079678a1095868980ed793dc968fd1715c6a375b
3
+ size 17711424
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cd95786eb7a382cfafb2008838ffe14ca84e71502d420fe039e3bce39cc3d5
3
+ size 5385887744
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748267773db18c68fb7ec0dfa4048f4cb601851f532f8ded9ca9b6da93366437
3
+ size 35431037
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cd95786eb7a382cfafb2008838ffe14ca84e71502d420fe039e3bce39cc3d5
3
+ size 5385887744
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6f9ff5a1259fbb88e0d7328ef58a9fa80d7252101261ec75444d3d42a7afde
3
+ size 17734650
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cd95786eb7a382cfafb2008838ffe14ca84e71502d420fe039e3bce39cc3d5
3
+ size 5385887744
onnx/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32013,
4
+ "eos_token_id": 32021,
5
+ "transformers_version": "4.34.0"
6
+ }
onnx/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<｜begin▁of▁sentence｜>",
3
+ "eos_token": "<|EOT|>",
4
+ "pad_token": "<｜end▁of▁sentence｜>"
5
+ }
onnx/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "32000": {
4
+ "content": "õ",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "32001": {
12
+ "content": "÷",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "32002": {
20
+ "content": "Á",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "32003": {
28
+ "content": "ý",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "32004": {
36
+ "content": "À",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "32005": {
44
+ "content": "ÿ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "32006": {
52
+ "content": "ø",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "32007": {
60
+ "content": "ú",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "32008": {
68
+ "content": "þ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "32009": {
76
+ "content": "ü",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "32010": {
84
+ "content": "ù",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "32011": {
92
+ "content": "ö",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "32012": {
100
+ "content": "û",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "32013": {
108
+ "content": "<｜begin▁of▁sentence｜>",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32014": {
116
+ "content": "<｜end▁of▁sentence｜>",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32015": {
124
+ "content": "<｜fim▁hole｜>",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "32016": {
132
+ "content": "<｜fim▁begin｜>",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "32017": {
140
+ "content": "<｜fim▁end｜>",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "32018": {
148
+ "content": "<pad>",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "32019": {
156
+ "content": "<|User|>",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "32020": {
164
+ "content": "<|Assistant|>",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "32021": {
172
+ "content": "<|EOT|>",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ }
179
+ },
180
+ "additional_special_tokens": [],
181
+ "bos_token": "<｜begin▁of▁sentence｜>",
182
+ "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
183
+ "clean_up_tokenization_spaces": false,
184
+ "eos_token": "<|EOT|>",
185
+ "legacy": true,
186
+ "model_max_length": 16384,
187
+ "pad_token": "<｜end▁of▁sentence｜>",
188
+ "sp_model_kwargs": {},
189
+ "tokenizer_class": "LlamaTokenizer",
190
+ "unk_token": null,
191
+ "use_default_system_prompt": true
192
+ }