jerseyjerry commited on
Commit
b9e7830
·
verified ·
1 Parent(s): 03d414b

Uploading model files

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: peft
3
  license: other
4
- base_model: microsoft/Phi-4-mini-instruct
5
  ---
6
 
7
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,6 +26,8 @@ More information needed
26
 
27
  ### Training hyperparameters
28
 
 
 
29
 
30
 
31
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
  license: other
4
+ base_model: Qwen/Qwen2.5-3B-Instruct
5
  ---
6
 
7
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
26
 
27
  ### Training hyperparameters
28
 
29
+ ### Training results
30
+
31
 
32
 
33
  ### Framework versions
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
@@ -13,24 +13,27 @@
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
- "lora_alpha": 64,
17
  "lora_bias": false,
18
- "lora_dropout": 0.1,
19
  "megatron_config": null,
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": null,
22
  "peft_type": "LORA",
23
- "r": 32,
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "down_proj",
28
  "o_proj",
29
- "gate_up_proj",
30
- "qkv_proj"
 
 
 
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "trainable_token_indices": null,
34
  "use_dora": false,
35
- "use_rslora": true
36
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
 
13
  "layers_pattern": null,
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
+ "lora_alpha": 256,
17
  "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
  "megatron_config": null,
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": null,
22
  "peft_type": "LORA",
23
+ "r": 128,
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "gate_proj",
28
  "o_proj",
29
+ "down_proj",
30
+ "up_proj",
31
+ "q_proj",
32
+ "v_proj",
33
+ "k_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
37
  "use_dora": false,
38
+ "use_rslora": false
39
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96539534c4692df48882f749e1c5335b1bd176f08763ef5aca6957105edffb0f
3
- size 184584072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6a8cd096af293e4d80a62466a23c493329025beb328d3e080c9eceefcde9d7
3
+ size 957942768
added_tokens.json CHANGED
@@ -1,13 +1,24 @@
1
  {
2
- "<|/tool_call|>": 200026,
3
- "<|/tool|>": 200024,
4
- "<|assistant|>": 200019,
5
- "<|end|>": 200020,
6
- "<|im_end|>": 200029,
7
- "<|system|>": 200022,
8
- "<|tag|>": 200028,
9
- "<|tool_call|>": 200025,
10
- "<|tool_response|>": 200027,
11
- "<|tool|>": 200023,
12
- "<|user|>": 200021
 
 
 
 
 
 
 
 
 
 
 
13
  }
 
1
  {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
  }
chat_template.jinja CHANGED
@@ -1 +1,54 @@
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 %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,11 +1,19 @@
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": "<|im_end|>",
11
  "lstrip": false,
@@ -19,12 +27,5 @@
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
  }
 
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,
 
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
 
 
 
 
 
 
 
30
  }
31
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8799b7ce62bf40e724f80af87b9545f9d9043778f435040a6c08e834dc047b69
3
- size 15524282
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json CHANGED
@@ -1,9 +1,8 @@
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,
@@ -11,111 +10,199 @@
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
- "200029": {
103
- "content": "<|im_end|>",
104
  "lstrip": false,
105
  "normalized": false,
106
  "rstrip": false,
107
  "single_word": false,
108
- "special": true
 
 
 
 
 
 
 
 
109
  }
110
  },
111
- "bos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
112
  "clean_up_tokenization_spaces": false,
113
  "eos_token": "<|im_end|>",
 
114
  "extra_special_tokens": {},
115
  "model_max_length": 131072,
116
  "pad_token": "<|endoftext|>",
117
  "padding_side": "right",
118
  "split_special_tokens": false,
119
- "tokenizer_class": "GPT2Tokenizer",
120
- "unk_token": "<|endoftext|>"
121
  }
 
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,
 
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
  },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
  "clean_up_tokenization_spaces": false,
199
  "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
  "extra_special_tokens": {},
202
  "model_max_length": 131072,
203
  "pad_token": "<|endoftext|>",
204
  "padding_side": "right",
205
  "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91a7473d33db7326dfd33d711b8248f2d0ec8796c98b6989084de8fc4d60103a
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033a5edeed20fb21308753824bcfbe12e3a38a0cf1e69a5fe9fc29dffe493a07
3
  size 6097
vocab.json CHANGED
The diff for this file is too large to render. See raw diff