Eddie-L commited on
Commit
facb3ad
·
verified ·
1 Parent(s): e63463b

Training in progress, step 40

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/functiongemma-270m-it
3
+ library_name: transformers
4
+ model_name: functiongemma-270m-it-simple-tool-calling
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for functiongemma-270m-it-simple-tool-calling
13
+
14
+ This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="Eddie-L/functiongemma-270m-it-simple-tool-calling", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+
34
+ This model was trained with SFT.
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 1.2.0
39
+ - Transformers: 5.6.2
40
+ - Pytorch: 2.11.0+cu126
41
+ - Datasets: 4.8.4
42
+ - Tokenizers: 0.22.2
43
+
44
+ ## Citations
45
+
46
+
47
+
48
+ Cite TRL as:
49
+
50
+ ```bibtex
51
+ @software{vonwerra2020trl,
52
+ title = {{TRL: Transformers Reinforcement Learning}},
53
+ author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
54
+ license = {Apache-2.0},
55
+ url = {https://github.com/huggingface/trl},
56
+ year = {2020}
57
+ }
58
+ ```
adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "google/functiongemma-270m-it",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 16,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "o_proj",
34
+ "k_proj",
35
+ "gate_proj",
36
+ "up_proj",
37
+ "q_proj",
38
+ "down_proj",
39
+ "v_proj"
40
+ ],
41
+ "target_parameters": null,
42
+ "task_type": "CAUSAL_LM",
43
+ "trainable_token_indices": null,
44
+ "use_bdlora": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23e6b8b392cea7fa31c1947779997ec2e5f6dfcaad43c9994a5e31bbdeb44bb
3
+ size 7627024
chat_template.jinja ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- macro format_parameters(properties, required) -%}
2
+ {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
3
+ {%- set ns = namespace(found_first=false) -%}
4
+ {%- for key, value in properties | dictsort -%}
5
+ {%- if key not in standard_keys -%}
6
+ {%- if ns.found_first %},{% endif -%}
7
+ {%- set ns.found_first = true -%}
8
+ {{- key }}:{description:<escape>{{ value['description'] }}<escape>
9
+ {%- if value['type'] | upper == 'STRING' -%}
10
+ {%- if value['enum'] -%}
11
+ ,enum:{{ format_argument(value['enum']) }}
12
+ {%- endif -%}
13
+ {%- elif value['type'] | upper == 'OBJECT' -%}
14
+ ,properties:{
15
+ {%- if value['properties'] is defined and value['properties'] is mapping -%}
16
+ {{- format_parameters(value['properties'], value['required'] | default([])) -}}
17
+ {%- elif value is mapping -%}
18
+ {{- format_parameters(value, value['required'] | default([])) -}}
19
+ {%- endif -%}
20
+ }
21
+ {%- if value['required'] -%}
22
+ ,required:[
23
+ {%- for item in value['required'] | default([]) -%}
24
+ <escape>{{- item -}}<escape>
25
+ {%- if not loop.last %},{% endif -%}
26
+ {%- endfor -%}
27
+ ]
28
+ {%- endif -%}
29
+ {%- elif value['type'] | upper == 'ARRAY' -%}
30
+ {%- if value['items'] is mapping and value['items'] -%}
31
+ ,items:{
32
+ {%- set ns_items = namespace(found_first=false) -%}
33
+ {%- for item_key, item_value in value['items'] | dictsort -%}
34
+ {%- if item_value is not none -%}
35
+ {%- if ns_items.found_first %},{% endif -%}
36
+ {%- set ns_items.found_first = true -%}
37
+ {%- if item_key == 'properties' -%}
38
+ properties:{
39
+ {%- if item_value is mapping -%}
40
+ {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
41
+ {%- endif -%}
42
+ }
43
+ {%- elif item_key == 'required' -%}
44
+ required:[
45
+ {%- for req_item in item_value -%}
46
+ <escape>{{- req_item -}}<escape>
47
+ {%- if not loop.last %},{% endif -%}
48
+ {%- endfor -%}
49
+ ]
50
+ {%- elif item_key == 'type' -%}
51
+ {%- if item_value is string -%}
52
+ type:{{ format_argument(item_value | upper) }}
53
+ {%- else -%}
54
+ type:{{ format_argument(item_value | map('upper') | list) }}
55
+ {%- endif -%}
56
+ {%- else -%}
57
+ {{ item_key }}:{{ format_argument(item_value) }}
58
+ {%- endif -%}
59
+ {%- endif -%}
60
+ {%- endfor -%}
61
+ }
62
+ {%- endif -%}
63
+ {%- endif -%}
64
+ ,type:<escape>{{ value['type'] | upper }}<escape>}
65
+ {%- endif -%}
66
+ {%- endfor -%}
67
+ {%- endmacro -%}
68
+ {% macro format_function_declaration(tool_data) -%}
69
+ declaration:{{- tool_data['function']['name'] -}}
70
+ {description:<escape>{{- tool_data['function']['description'] -}}<escape>
71
+ {%- set params = tool_data['function']['parameters'] -%}
72
+ {%- if params -%}
73
+ ,parameters:{
74
+ {%- if params['properties'] -%}
75
+ properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
76
+ {%- endif -%}
77
+ {%- if params['required'] -%}
78
+ required:[
79
+ {%- for item in params['required'] -%}
80
+ <escape>{{- item -}}<escape>
81
+ {{- ',' if not loop.last -}}
82
+ {%- endfor -%}
83
+ ],
84
+ {%- endif -%}
85
+ {%- if params['type'] -%}
86
+ type:<escape>{{- params['type'] | upper -}}<escape>}
87
+ {%- endif -%}
88
+ {%- endif -%}
89
+ }
90
+ {%- endmacro -%}
91
+ {% macro format_argument(argument, escape_keys=True) -%}
92
+ {%- if argument is string -%}
93
+ {{- '<escape>' + argument + '<escape>' -}}
94
+ {%- elif argument is boolean -%}
95
+ {%- if argument -%}
96
+ {{- 'true' -}}
97
+ {%- else -%}
98
+ {{- 'false' -}}
99
+ {%- endif -%}
100
+ {%- elif argument is mapping -%}
101
+ {{- '{' -}}
102
+ {%- set ns = namespace(found_first=false) -%}
103
+ {%- for key, value in argument | dictsort -%}
104
+ {%- if ns.found_first %},{% endif -%}
105
+ {%- set ns.found_first = true -%}
106
+ {%- if escape_keys -%}
107
+ {{- '<escape>' + key + '<escape>' -}}
108
+ {%- else -%}
109
+ {{- key -}}
110
+ {%- endif -%}
111
+ :{{- format_argument(value, escape_keys=escape_keys) -}}
112
+ {%- endfor -%}
113
+ {{- '}' -}}
114
+ {%- elif argument is sequence -%}
115
+ {{- '[' -}}
116
+ {%- for item in argument -%}
117
+ {{- format_argument(item, escape_keys=escape_keys) -}}
118
+ {%- if not loop.last %},{% endif -%}
119
+ {%- endfor -%}
120
+ {{- ']' -}}
121
+ {%- else -%}
122
+ {{- argument -}}
123
+ {%- endif -%}
124
+ {%- endmacro -%}
125
+ {{ bos_token }}
126
+ {%- set ns = namespace(prev_message_type=None) -%}
127
+ {#- Tool Declarations -#}
128
+ {%- set loop_messages = messages -%}
129
+ {%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
130
+ {{- '<start_of_turn>developer\n' -}}
131
+ {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
132
+ {%- if messages[0]['content'] is string -%}
133
+ {{- messages[0]['content'] | trim -}}
134
+ {%- elif messages[0]['content'] is sequence -%}
135
+ {%- for item in messages[0]['content'] -%}
136
+ {%- if item['type'] == 'text' -%}
137
+ {{- item['text'] | trim -}}
138
+ {%- endif -%}
139
+ {%- endfor -%}
140
+ {%- endif -%}
141
+ {%- set loop_messages = messages[1:] -%}
142
+ {%- endif -%}
143
+ {%- if tools -%}
144
+ {%- for tool in tools %}
145
+ {{- '<start_function_declaration>' -}}
146
+ {{- format_function_declaration(tool) | trim }}
147
+ {{- '<end_function_declaration>' -}}
148
+ {%- endfor %}
149
+ {%- endif -%}
150
+ {{- '<end_of_turn>\n' }}
151
+ {%- endif %}
152
+ {#- Loop through messages. -#}
153
+ {%- for message in loop_messages -%}
154
+ {%- if (message['role'] == 'assistant') -%}
155
+ {#- Rename "assistant" to "model". -#}
156
+ {%- set role = "model" -%}
157
+ {%- else -%}
158
+ {%- set role = message['role'] -%}
159
+ {%- endif -%}
160
+ {%- if role != 'tool' -%}
161
+ {%- if ns.prev_message_type != 'tool_response' -%}
162
+ {{- '<start_of_turn>' + role + '\n' }}
163
+ {%- endif -%}
164
+ {%- set ns.prev_message_type = None -%}
165
+ {%- if 'content' in message and message['content'] is not none -%}
166
+ {%- if message['content'] is string -%}
167
+ {{ message['content'] | trim }}
168
+ {%- elif message['content'] is sequence -%}
169
+ {%- for item in message['content'] -%}
170
+ {%- if item['type'] == 'image' -%}
171
+ {{ '<start_of_image>' }}
172
+ {%- elif item['type'] == 'text' -%}
173
+ {{ item['text'] | trim }}
174
+ {%- endif -%}
175
+ {%- endfor -%}
176
+ {%- else -%}
177
+ {{ raise_exception("Invalid content type in user/assistant message") }}
178
+ {%- endif -%}
179
+ {%- set ns.prev_message_type = 'content' -%}
180
+ {%- endif -%}
181
+ {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
182
+ {#- Tool Calls -#}
183
+ {%- for tool_call in message['tool_calls'] -%}
184
+ {% set function = tool_call['function'] %}
185
+ {{- '<start_function_call>call:' + function['name'] + '{' -}}
186
+ {%- if 'arguments' in function -%}
187
+ {%- if function['arguments'] is mapping -%}
188
+ {%- set ns = namespace(found_first=false) -%}
189
+ {%- for key, value in function['arguments'] | dictsort -%}
190
+ {%- if ns.found_first %},{% endif -%}
191
+ {%- set ns.found_first = true -%}
192
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
193
+ {%- endfor -%}
194
+ {%- elif function['arguments'] is string -%}
195
+ {# This handles string-JSON, just in case #}
196
+ {{ function['arguments'] }}
197
+ {%- endif %}
198
+ {%- endif -%}
199
+ {{- '}<end_function_call>' -}}
200
+ {%- endfor -%}
201
+ {%- if loop.last -%}
202
+ {{ '<start_function_response>' }}
203
+ {%- endif -%}
204
+ {%- set ns.prev_message_type = 'tool_call' -%}
205
+ {%- endif -%}
206
+ {%- else -%}
207
+ {#- Tool Responses -#}
208
+ {%- if 'content' in message and message['content'] -%}
209
+ {%- if message['content'] is mapping -%}
210
+ {%- if 'name' in message['content'] and 'response' in message['content'] -%}
211
+ {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
212
+ {%- set response_ns = namespace(found_first=false) -%}
213
+ {%- for key, value in message['content']['response'] | dictsort -%}
214
+ {%- if response_ns.found_first %},{% endif -%}
215
+ {%- set response_ns.found_first = true -%}
216
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
217
+ {%- endfor -%}
218
+ {{- '}<end_function_response>' -}}
219
+ {%- elif 'name' in message -%}
220
+ {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
221
+ {%- set response_ns = namespace(found_first=false) -%}
222
+ {%- for key, value in message['content'] | dictsort -%}
223
+ {%- if response_ns.found_first %},{% endif -%}
224
+ {%- set response_ns.found_first = true -%}
225
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
226
+ {%- endfor -%}
227
+ {{- '}<end_function_response>' -}}
228
+ {%- else -%}
229
+ {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
230
+ {%- endif -%}
231
+ {%- elif message['content'] is string -%}
232
+ {%- if 'name' in message -%}
233
+ {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
234
+ {%- else -%}
235
+ {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
236
+ {%- endif -%}
237
+ {%- elif message['content'] is sequence -%}
238
+ {%- for item in message['content'] -%}
239
+ {%- if item is mapping -%}
240
+ {%- if 'name' in item and 'response' in item -%}
241
+ {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
242
+ {%- set response_ns = namespace(found_first=false) -%}
243
+ {%- for key, value in item['response'] | dictsort -%}
244
+ {%- if response_ns.found_first %},{% endif -%}
245
+ {%- set response_ns.found_first = true -%}
246
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
247
+ {%- endfor -%}
248
+ {{- '}<end_function_response>' -}}
249
+ {%- elif 'name' in message -%}
250
+ {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
251
+ {%- set response_ns = namespace(found_first=false) -%}
252
+ {%- for key, value in item | dictsort -%}
253
+ {%- if response_ns.found_first %},{% endif -%}
254
+ {%- set response_ns.found_first = true -%}
255
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
256
+ {%- endfor -%}
257
+ {{- '}<end_function_response>' -}}
258
+ {%- else -%}
259
+ {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
260
+ {%- endif -%}
261
+ {%- else -%}
262
+ {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
263
+ {%- endif -%}
264
+ {%- endfor -%}
265
+ {%- else -%}
266
+ {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
267
+ {%- endif -%}
268
+ {%- endif -%}
269
+ {%- set ns.prev_message_type = 'tool_response' -%}
270
+ {%- endif -%}
271
+ {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
272
+ {{ '<end_of_turn>\n' }}
273
+ {%- endif -%}
274
+ {%- endfor -%}
275
+ {%- if add_generation_prompt -%}
276
+ {%- if ns.prev_message_type != 'tool_response' -%}
277
+ {{- '<start_of_turn>model\n' -}}
278
+ {%- endif -%}
279
+ {%- endif -%}
runs/Apr25_09-24-10_Game/events.out.tfevents.1777080250.Game.56644.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e70cd34069a22302150ae0e89698608d3a47fa338dd9b4fe5aa39b1b49c2f8a
3
+ size 24286
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
3
+ size 33384898
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "boi_token": "<start_of_image>",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eoi_token": "<end_of_image>",
7
+ "eos_token": "<eos>",
8
+ "image_token": "<image_soft_token>",
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "mask_token": "<mask>",
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "model_specific_special_tokens": {
14
+ "boi_token": "<start_of_image>",
15
+ "eoi_token": "<end_of_image>",
16
+ "image_token": "<image_soft_token>",
17
+ "sfr_token": "<start_function_response>"
18
+ },
19
+ "pad_token": "<pad>",
20
+ "padding_side": "left",
21
+ "sfr_token": "<start_function_response>",
22
+ "sp_model_kwargs": null,
23
+ "spaces_between_special_tokens": false,
24
+ "tokenizer_class": "GemmaTokenizer",
25
+ "unk_token": "<unk>",
26
+ "use_default_system_prompt": false
27
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a93bb97cebc3ee82c437e2263b22167456b5521cdec43ee90358cc554318c87
3
+ size 5777