Xiaofei Han commited on
Commit
bc1a2fc
·
1 Parent(s): 52a17d5

upload model

Browse files
Files changed (46) hide show
  1. DeepSeek-R1-Distill-Qwen-1.5B/chat_template.jinja +1 -0
  2. DeepSeek-R1-Distill-Qwen-1.5B/genai_config.json +55 -0
  3. DeepSeek-R1-Distill-Qwen-1.5B/model.onnx +3 -0
  4. DeepSeek-R1-Distill-Qwen-1.5B/model.onnx.data +3 -0
  5. DeepSeek-R1-Distill-Qwen-1.5B/special_tokens_map.json +23 -0
  6. DeepSeek-R1-Distill-Qwen-1.5B/tokenizer.json +3 -0
  7. DeepSeek-R1-Distill-Qwen-1.5B/tokenizer_config.json +194 -0
  8. Phi-4-mini-instruct-ROE/added_tokens.json +12 -0
  9. Phi-4-mini-instruct-ROE/genai_config.json +58 -0
  10. Phi-4-mini-instruct-ROE/merges.txt +0 -0
  11. Phi-4-mini-instruct-ROE/model.onnx +3 -0
  12. Phi-4-mini-instruct-ROE/model.onnx.data +3 -0
  13. Phi-4-mini-instruct-ROE/special_tokens_map.json +30 -0
  14. Phi-4-mini-instruct-ROE/tokenizer.json +3 -0
  15. Phi-4-mini-instruct-ROE/tokenizer_config.json +112 -0
  16. Phi-4-mini-instruct-ROE/vocab.json +0 -0
  17. Phi-4-mini-instruct-nonROE/.cipdpkg/manifest.json +4 -0
  18. Phi-4-mini-instruct-nonROE/added_tokens.json +12 -0
  19. Phi-4-mini-instruct-nonROE/chat_template.jinja +1 -0
  20. Phi-4-mini-instruct-nonROE/edge_on_device_model_execution_config.pb +3 -0
  21. Phi-4-mini-instruct-nonROE/genai_config.json +59 -0
  22. Phi-4-mini-instruct-nonROE/manifest.json +0 -0
  23. Phi-4-mini-instruct-nonROE/merges.txt +0 -0
  24. Phi-4-mini-instruct-nonROE/model.onnx +3 -0
  25. Phi-4-mini-instruct-nonROE/model.onnx.data +3 -0
  26. Phi-4-mini-instruct-nonROE/special_tokens_map.json +30 -0
  27. Phi-4-mini-instruct-nonROE/tokenizer.json +3 -0
  28. Phi-4-mini-instruct-nonROE/tokenizer_config.json +112 -0
  29. Phi-4-mini-instruct-nonROE/vocab.json +0 -0
  30. Qwen3-4B-Instruct-2507/added_tokens.json +28 -0
  31. Qwen3-4B-Instruct-2507/chat_template.jinja +61 -0
  32. Qwen3-4B-Instruct-2507/genai_config.json +58 -0
  33. Qwen3-4B-Instruct-2507/merges.txt +0 -0
  34. Qwen3-4B-Instruct-2507/model.onnx +3 -0
  35. Qwen3-4B-Instruct-2507/model.onnx.data +3 -0
  36. Qwen3-4B-Instruct-2507/special_tokens_map.json +31 -0
  37. Qwen3-4B-Instruct-2507/tokenizer.json +3 -0
  38. Qwen3-4B-Instruct-2507/tokenizer_config.json +239 -0
  39. Qwen3-4B-Instruct-2507/vocab.json +0 -0
  40. gemma-3-270m-it/chat_template.jinja +47 -0
  41. gemma-3-270m-it/genai_config.json +58 -0
  42. gemma-3-270m-it/model.onnx +3 -0
  43. gemma-3-270m-it/model.onnx.data +3 -0
  44. gemma-3-270m-it/special_tokens_map.json +33 -0
  45. gemma-3-270m-it/tokenizer.json +3 -0
  46. gemma-3-270m-it/tokenizer_config.json +0 -0
DeepSeek-R1-Distill-Qwen-1.5B/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
DeepSeek-R1-Distill-Qwen-1.5B/genai_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 151646,
4
+ "context_length": 131072,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "webgpu": {
11
+ "ep.webgpuexecutionprovider.validationMode": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "model.onnx",
17
+ "head_size": 128,
18
+ "hidden_size": 1536,
19
+ "inputs": {
20
+ "input_ids": "input_ids",
21
+ "attention_mask": "attention_mask",
22
+ "past_key_names": "past_key_values.%d.key",
23
+ "past_value_names": "past_key_values.%d.value"
24
+ },
25
+ "outputs": {
26
+ "logits": "logits",
27
+ "present_key_names": "present.%d.key",
28
+ "present_value_names": "present.%d.value"
29
+ },
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 28,
32
+ "num_key_value_heads": 2
33
+ },
34
+ "eos_token_id": 151643,
35
+ "pad_token_id": 151643,
36
+ "type": "qwen2",
37
+ "vocab_size": 151936
38
+ },
39
+ "search": {
40
+ "diversity_penalty": 0.0,
41
+ "do_sample": true,
42
+ "early_stopping": true,
43
+ "length_penalty": 1.0,
44
+ "max_length": 2048,
45
+ "min_length": 0,
46
+ "no_repeat_ngram_size": 0,
47
+ "num_beams": 1,
48
+ "num_return_sequences": 1,
49
+ "past_present_share_buffer": false,
50
+ "repetition_penalty": 1.0,
51
+ "temperature": 0.6,
52
+ "top_k": 50,
53
+ "top_p": 0.95
54
+ }
55
+ }
DeepSeek-R1-Distill-Qwen-1.5B/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cda8e7a4cbfe1a4a707d55ca82befe8067a82c8c5ffc671f395b82538574b9a
3
+ size 254828
DeepSeek-R1-Distill-Qwen-1.5B/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be11f943cf58e0f664b734827d9b01cabdaaea89f83b7c586f1ed6db6b09c35
3
+ size 1513422848
DeepSeek-R1-Distill-Qwen-1.5B/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
DeepSeek-R1-Distill-Qwen-1.5B/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
DeepSeek-R1-Distill-Qwen-1.5B/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|end▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|User|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<|Assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<|begin▁of▁sentence|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<|begin▁of▁sentence|>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|end▁of▁sentence|>",
186
+ "extra_special_tokens": {},
187
+ "legacy": true,
188
+ "model_max_length": 16384,
189
+ "pad_token": "<|end▁of▁sentence|>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizerFast",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
Phi-4-mini-instruct-ROE/added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
Phi-4-mini-instruct-ROE/genai_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 199999,
4
+ "context_length": 131072,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "webgpu": {
11
+ "ep.webgpuexecutionprovider.validationMode": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "model.onnx",
17
+ "head_size": 128,
18
+ "hidden_size": 3072,
19
+ "inputs": {
20
+ "input_ids": "input_ids",
21
+ "attention_mask": "attention_mask",
22
+ "past_key_names": "past_key_values.%d.key",
23
+ "past_value_names": "past_key_values.%d.value"
24
+ },
25
+ "outputs": {
26
+ "logits": "logits",
27
+ "present_key_names": "present.%d.key",
28
+ "present_value_names": "present.%d.value"
29
+ },
30
+ "num_attention_heads": 24,
31
+ "num_hidden_layers": 32,
32
+ "num_key_value_heads": 8
33
+ },
34
+ "eos_token_id": [
35
+ 200020,
36
+ 199999
37
+ ],
38
+ "pad_token_id": 199999,
39
+ "type": "phi3",
40
+ "vocab_size": 200064
41
+ },
42
+ "search": {
43
+ "diversity_penalty": 0.0,
44
+ "do_sample": false,
45
+ "early_stopping": true,
46
+ "length_penalty": 1.0,
47
+ "max_length": 2048,
48
+ "min_length": 0,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beams": 1,
51
+ "num_return_sequences": 1,
52
+ "past_present_share_buffer": false,
53
+ "repetition_penalty": 1.0,
54
+ "temperature": 1.0,
55
+ "top_k": 50,
56
+ "top_p": 1.0
57
+ }
58
+ }
Phi-4-mini-instruct-ROE/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Phi-4-mini-instruct-ROE/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a79fbe96825974b67ac06231f97a29ef3abbaf19f6235e180549718c1d4e7b5
3
+ size 26192834
Phi-4-mini-instruct-ROE/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eac8013883d775e4280183fdc3b41969499580cfd865297e1f11c6179e27a13
3
+ size 2465347584
Phi-4-mini-instruct-ROE/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
Phi-4-mini-instruct-ROE/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
Phi-4-mini-instruct-ROE/tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "199999": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "200018": {
15
+ "content": "<|endofprompt|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "200019": {
23
+ "content": "<|assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "200020": {
31
+ "content": "<|end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "200021": {
39
+ "content": "<|user|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "200022": {
47
+ "content": "<|system|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "200023": {
55
+ "content": "<|tool|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "200024": {
63
+ "content": "<|/tool|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "200025": {
71
+ "content": "<|tool_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "200026": {
79
+ "content": "<|/tool_call|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "200027": {
87
+ "content": "<|tool_response|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "200028": {
95
+ "content": "<|tag|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ }
102
+ },
103
+ "bos_token": "<|endoftext|>",
104
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
105
+ "clean_up_tokenization_spaces": false,
106
+ "eos_token": "<|endoftext|>",
107
+ "extra_special_tokens": {},
108
+ "model_max_length": 131072,
109
+ "pad_token": "<|endoftext|>",
110
+ "tokenizer_class": "GPT2Tokenizer",
111
+ "unk_token": "<|endoftext|>"
112
+ }
Phi-4-mini-instruct-ROE/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
Phi-4-mini-instruct-nonROE/.cipdpkg/manifest.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "format_version": "1.1",
3
+ "package_name": "edge-llm-fp16-on-device-model"
4
+ }
Phi-4-mini-instruct-nonROE/added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
Phi-4-mini-instruct-nonROE/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
Phi-4-mini-instruct-nonROE/edge_on_device_model_execution_config.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4c5a5cf01a1ab9864e8575c92dc8e598bf5dbac6d54e59b18a818025dde6e5
3
+ size 7156
Phi-4-mini-instruct-nonROE/genai_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 199999,
4
+ "context_length": 131072,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "webgpu": {
11
+ "ep.webgpuexecutionprovider.validationMode": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "model.onnx",
17
+ "head_size": 128,
18
+ "hidden_size": 3072,
19
+ "inputs": {
20
+ "input_ids": "input_ids",
21
+ "attention_mask": "attention_mask",
22
+ "position_ids": "position_ids",
23
+ "past_key_names": "past_key_values.%d.key",
24
+ "past_value_names": "past_key_values.%d.value"
25
+ },
26
+ "outputs": {
27
+ "logits": "logits",
28
+ "present_key_names": "present.%d.key",
29
+ "present_value_names": "present.%d.value"
30
+ },
31
+ "num_attention_heads": 24,
32
+ "num_hidden_layers": 32,
33
+ "num_key_value_heads": 8
34
+ },
35
+ "eos_token_id": [
36
+ 200020,
37
+ 199999
38
+ ],
39
+ "pad_token_id": 199999,
40
+ "type": "phi3",
41
+ "vocab_size": 200064
42
+ },
43
+ "search": {
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "early_stopping": true,
47
+ "length_penalty": 1.0,
48
+ "max_length": 2048,
49
+ "min_length": 0,
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "past_present_share_buffer": false,
54
+ "repetition_penalty": 1.0,
55
+ "temperature": 1.0,
56
+ "top_k": 1,
57
+ "top_p": 1.0
58
+ }
59
+ }
Phi-4-mini-instruct-nonROE/manifest.json ADDED
Binary file (1.02 kB). View file
 
Phi-4-mini-instruct-nonROE/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Phi-4-mini-instruct-nonROE/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e79adb42d84794fb15ebdcc785e17c8e987e1b0203190e5c200dfdcf46e6c76
3
+ size 26246312
Phi-4-mini-instruct-nonROE/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b492da1c068ace8a3250c2a0e39ed61ede647c739b239c056a27cc4b66d40fb
3
+ size 2465347584
Phi-4-mini-instruct-nonROE/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
Phi-4-mini-instruct-nonROE/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
Phi-4-mini-instruct-nonROE/tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "add_bos_token": false,
4
+ "add_eos_token": false,
5
+ "add_prefix_space": false,
6
+ "added_tokens_decoder": {
7
+ "199999": {
8
+ "content": "<|endoftext|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false,
13
+ "special": true
14
+ },
15
+ "200018": {
16
+ "content": "<|endofprompt|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false,
21
+ "special": true
22
+ },
23
+ "200019": {
24
+ "content": "<|assistant|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false,
29
+ "special": true
30
+ },
31
+ "200020": {
32
+ "content": "<|end|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": true,
36
+ "single_word": false,
37
+ "special": true
38
+ },
39
+ "200021": {
40
+ "content": "<|user|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": true,
44
+ "single_word": false,
45
+ "special": true
46
+ },
47
+ "200022": {
48
+ "content": "<|system|>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": true,
52
+ "single_word": false,
53
+ "special": true
54
+ },
55
+ "200023": {
56
+ "content": "<|tool|>",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": true,
60
+ "single_word": false,
61
+ "special": false
62
+ },
63
+ "200024": {
64
+ "content": "<|/tool|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": true,
68
+ "single_word": false,
69
+ "special": false
70
+ },
71
+ "200025": {
72
+ "content": "<|tool_call|>",
73
+ "lstrip": false,
74
+ "normalized": false,
75
+ "rstrip": true,
76
+ "single_word": false,
77
+ "special": false
78
+ },
79
+ "200026": {
80
+ "content": "<|/tool_call|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": true,
84
+ "single_word": false,
85
+ "special": false
86
+ },
87
+ "200027": {
88
+ "content": "<|tool_response|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": true,
92
+ "single_word": false,
93
+ "special": false
94
+ },
95
+ "200028": {
96
+ "content": "<|tag|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": true,
100
+ "single_word": false,
101
+ "special": true
102
+ }
103
+ },
104
+ "bos_token": "<|endoftext|>",
105
+ "clean_up_tokenization_spaces": false,
106
+ "eos_token": "<|endoftext|>",
107
+ "extra_special_tokens": {},
108
+ "model_max_length": 131072,
109
+ "pad_token": "<|endoftext|>",
110
+ "tokenizer_class": "GPT2Tokenizer",
111
+ "unk_token": "<|endoftext|>"
112
+ }
Phi-4-mini-instruct-nonROE/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-4B-Instruct-2507/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
Qwen3-4B-Instruct-2507/chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- endif %}
Qwen3-4B-Instruct-2507/genai_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 151643,
4
+ "context_length": 262144,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "webgpu": {
11
+ "ep.webgpuexecutionprovider.validationMode": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "model.onnx",
17
+ "head_size": 128,
18
+ "hidden_size": 2560,
19
+ "inputs": {
20
+ "input_ids": "input_ids",
21
+ "attention_mask": "attention_mask",
22
+ "past_key_names": "past_key_values.%d.key",
23
+ "past_value_names": "past_key_values.%d.value"
24
+ },
25
+ "outputs": {
26
+ "logits": "logits",
27
+ "present_key_names": "present.%d.key",
28
+ "present_value_names": "present.%d.value"
29
+ },
30
+ "num_attention_heads": 32,
31
+ "num_hidden_layers": 36,
32
+ "num_key_value_heads": 8
33
+ },
34
+ "eos_token_id": [
35
+ 151645,
36
+ 151643
37
+ ],
38
+ "pad_token_id": 151643,
39
+ "type": "qwen3",
40
+ "vocab_size": 151936
41
+ },
42
+ "search": {
43
+ "diversity_penalty": 0.0,
44
+ "do_sample": true,
45
+ "early_stopping": true,
46
+ "length_penalty": 1.0,
47
+ "max_length": 2048,
48
+ "min_length": 0,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beams": 1,
51
+ "num_return_sequences": 1,
52
+ "past_present_share_buffer": false,
53
+ "repetition_penalty": 1.0,
54
+ "temperature": 0.7,
55
+ "top_k": 20,
56
+ "top_p": 0.8
57
+ }
58
+ }
Qwen3-4B-Instruct-2507/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen3-4B-Instruct-2507/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb612767a2eade689451a3cd49f157cdf2b87b60a613c0f79318764eacb36def
3
+ size 480643
Qwen3-4B-Instruct-2507/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f603f6a2bef9f846959fddaace855987da401794f2c616192133b216c0fcf966
3
+ size 2595291136
Qwen3-4B-Instruct-2507/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
Qwen3-4B-Instruct-2507/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
Qwen3-4B-Instruct-2507/tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
Qwen3-4B-Instruct-2507/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
gemma-3-270m-it/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
gemma-3-270m-it/genai_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 2,
4
+ "context_length": 32768,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": [
9
+ {
10
+ "webgpu": {
11
+ "ep.webgpuexecutionprovider.validationMode": "0"
12
+ }
13
+ }
14
+ ]
15
+ },
16
+ "filename": "model.onnx",
17
+ "head_size": 256,
18
+ "hidden_size": 640,
19
+ "inputs": {
20
+ "input_ids": "input_ids",
21
+ "attention_mask": "attention_mask",
22
+ "past_key_names": "past_key_values.%d.key",
23
+ "past_value_names": "past_key_values.%d.value"
24
+ },
25
+ "outputs": {
26
+ "logits": "logits",
27
+ "present_key_names": "present.%d.key",
28
+ "present_value_names": "present.%d.value"
29
+ },
30
+ "num_attention_heads": 4,
31
+ "num_hidden_layers": 18,
32
+ "num_key_value_heads": 1
33
+ },
34
+ "eos_token_id": [
35
+ 1,
36
+ 106
37
+ ],
38
+ "pad_token_id": 0,
39
+ "type": "gemma3_text",
40
+ "vocab_size": 262144
41
+ },
42
+ "search": {
43
+ "diversity_penalty": 0.0,
44
+ "do_sample": true,
45
+ "early_stopping": true,
46
+ "length_penalty": 1.0,
47
+ "max_length": 2048,
48
+ "min_length": 0,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beams": 1,
51
+ "num_return_sequences": 1,
52
+ "past_present_share_buffer": false,
53
+ "repetition_penalty": 1.0,
54
+ "temperature": 1.0,
55
+ "top_k": 64,
56
+ "top_p": 0.95
57
+ }
58
+ }
gemma-3-270m-it/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd61bbc0fc25231549392aa8623a73ab002b571bfb356cea9a50495130230ac8
3
+ size 315554
gemma-3-270m-it/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca8288005257f444c0cf4eb1cbc7baacee7cb700e2b94b5b840387013d0d6e42
3
+ size 275251200
gemma-3-270m-it/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
gemma-3-270m-it/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
gemma-3-270m-it/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff