bebechien commited on
Commit
185fa7b
·
verified ·
1 Parent(s): bddbbad

Training in progress, epoch 1

Browse files
README.md CHANGED
@@ -1,17 +1,17 @@
1
  ---
2
- base_model: google/gemma-3-1b-pt
3
  library_name: transformers
4
  model_name: gemma-text-to-sql
5
  tags:
6
  - generated_from_trainer
7
- - trl
8
  - sft
 
9
  licence: license
10
  ---
11
 
12
  # Model Card for gemma-text-to-sql
13
 
14
- This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -30,15 +30,16 @@ print(output["generated_text"])
30
 
31
 
32
 
 
33
  This model was trained with SFT.
34
 
35
  ### Framework versions
36
 
37
- - TRL: 0.15.2
38
- - Transformers: 4.50.0.dev0
39
- - Pytorch: 2.9.0+cu126
40
- - Datasets: 3.3.2
41
- - Tokenizers: 0.21.4
42
 
43
  ## Citations
44
 
@@ -47,12 +48,11 @@ This model was trained with SFT.
47
  Cite TRL as:
48
 
49
  ```bibtex
50
- @misc{vonwerra2022trl,
51
- title = {{TRL: Transformer Reinforcement Learning}},
52
- author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
53
- year = 2020,
54
- journal = {GitHub repository},
55
- publisher = {GitHub},
56
- howpublished = {\url{https://github.com/huggingface/trl}}
57
  }
58
  ```
 
1
  ---
2
+ base_model: google/gemma-4-E2B
3
  library_name: transformers
4
  model_name: gemma-text-to-sql
5
  tags:
6
  - generated_from_trainer
 
7
  - sft
8
+ - trl
9
  licence: license
10
  ---
11
 
12
  # Model Card for gemma-text-to-sql
13
 
14
+ This model is a fine-tuned version of [google/gemma-4-E2B](https://huggingface.co/google/gemma-4-E2B).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
30
 
31
 
32
 
33
+
34
  This model was trained with SFT.
35
 
36
  ### Framework versions
37
 
38
+ - TRL: 1.6.0
39
+ - Transformers: 5.12.0
40
+ - Pytorch: 2.11.0+cu128
41
+ - Datasets: 5.0.0
42
+ - Tokenizers: 0.22.2
43
 
44
  ## Citations
45
 
 
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 CHANGED
@@ -1,8 +1,12 @@
1
  {
 
2
  "alpha_pattern": {},
 
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "google/gemma-3-1b-pt",
5
  "bias": "none",
 
 
6
  "eva_config": null,
7
  "exclude_modules": null,
8
  "fan_in_fan_out": false,
@@ -15,26 +19,25 @@
15
  "lora_alpha": 16,
16
  "lora_bias": false,
17
  "lora_dropout": 0.05,
 
18
  "megatron_config": null,
19
  "megatron_core": "megatron.core",
20
  "modules_to_save": [
21
- "lm_head",
22
- "embed_tokens"
23
  ],
24
  "peft_type": "LORA",
 
 
25
  "r": 16,
26
  "rank_pattern": {},
27
  "revision": null,
28
- "target_modules": [
29
- "v_proj",
30
- "down_proj",
31
- "k_proj",
32
- "up_proj",
33
- "o_proj",
34
- "q_proj",
35
- "gate_proj"
36
- ],
37
  "task_type": "CAUSAL_LM",
 
 
38
  "use_dora": false,
 
39
  "use_rslora": false
40
  }
 
1
  {
2
+ "alora_invocation_tokens": null,
3
  "alpha_pattern": {},
4
+ "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "google/gemma-4-E2B",
7
  "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": true,
10
  "eva_config": null,
11
  "exclude_modules": null,
12
  "fan_in_fan_out": false,
 
19
  "lora_alpha": 16,
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": [
26
+ "embed_tokens",
27
+ "model.language_model.embed_tokens"
28
  ],
29
  "peft_type": "LORA",
30
+ "peft_version": "0.19.1",
31
+ "qalora_group_size": 16,
32
  "r": 16,
33
  "rank_pattern": {},
34
  "revision": null,
35
+ "target_modules": ".*language_model\\..*\\.(q_proj|v_proj)",
36
+ "target_parameters": null,
 
 
 
 
 
 
 
37
  "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_bdlora": null,
40
  "use_dora": false,
41
+ "use_qalora": false,
42
  "use_rslora": false
43
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dec31ff42ca0f257b9d33e4fac7a362ddc410c59b8414ed38555213cad2899a9
3
- size 1260191096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd391f8189e3344d182a4cd609b06523eec90c6c887900a6e9d3c7e08e953250
3
+ size 1615986032
chat_template.jinja CHANGED
@@ -1,47 +1,360 @@
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 -%}
 
 
1
+ {%- macro format_parameters(properties, required, filter_keys=false) -%}
2
+ {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
3
+ {%- set ns = namespace(found_first=false) -%}
4
+ {%- for key, value in properties | dictsort -%}
5
+ {%- set add_comma = false -%}
6
+ {%- if not filter_keys or key not in standard_keys -%}
7
+ {%- if ns.found_first %},{% endif -%}
8
+ {%- set ns.found_first = true -%}
9
+ {{ key }}:{
10
+ {%- if value['description'] -%}
11
+ description:<|"|>{{ value['description'] }}<|"|>
12
+ {%- set add_comma = true -%}
13
+ {%- endif -%}
14
+ {%- if value['type'] | upper == 'STRING' -%}
15
+ {%- if value['enum'] -%}
16
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
17
+ enum:{{ format_argument(value['enum']) }}
18
+ {%- endif -%}
19
+ {%- elif value['type'] | upper == 'ARRAY' -%}
20
+ {%- if value['items'] is mapping and value['items'] -%}
21
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
22
+ items:{
23
+ {%- set ns_items = namespace(found_first=false) -%}
24
+ {%- for item_key, item_value in value['items'] | dictsort -%}
25
+ {%- if item_value is not none -%}
26
+ {%- if ns_items.found_first %},{% endif -%}
27
+ {%- set ns_items.found_first = true -%}
28
+ {%- if item_key == 'properties' -%}
29
+ properties:{
30
+ {%- if item_value is mapping -%}
31
+ {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
32
+ {%- endif -%}
33
+ }
34
+ {%- elif item_key == 'required' -%}
35
+ required:[
36
+ {%- for req_item in item_value -%}
37
+ <|"|>{{- req_item -}}<|"|>
38
+ {%- if not loop.last %},{% endif -%}
39
+ {%- endfor -%}
40
+ ]
41
+ {%- elif item_key == 'type' -%}
42
+ {%- if item_value is string -%}
43
+ type:{{ format_argument(item_value | upper) }}
44
+ {%- else -%}
45
+ type:{{ format_argument(item_value | map('upper') | list) }}
46
+ {%- endif -%}
47
+ {%- else -%}
48
+ {{ item_key }}:{{ format_argument(item_value) }}
49
+ {%- endif -%}
50
+ {%- endif -%}
51
+ {%- endfor -%}
52
+ }
53
+ {%- endif -%}
54
+ {%- endif -%}
55
+ {%- if value['nullable'] %}
56
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
57
+ nullable:true
58
+ {%- endif -%}
59
+ {%- if value['type'] | upper == 'OBJECT' -%}
60
+ {%- if value['properties'] is defined and value['properties'] is mapping -%}
61
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
62
+ properties:{
63
+ {{- format_parameters(value['properties'], value['required'] | default([])) -}}
64
+ }
65
+ {%- elif value is mapping -%}
66
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
67
+ properties:{
68
+ {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
69
+ }
70
+ {%- endif -%}
71
+ {%- if value['required'] -%}
72
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
73
+ required:[
74
+ {%- for item in value['required'] | default([]) -%}
75
+ <|"|>{{- item -}}<|"|>
76
+ {%- if not loop.last %},{% endif -%}
77
+ {%- endfor -%}
78
+ ]
79
+ {%- endif -%}
80
+ {%- endif -%}
81
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
82
+ type:<|"|>{{ value['type'] | upper }}<|"|>}
83
+ {%- endif -%}
84
+ {%- endfor -%}
85
+ {%- endmacro -%}
86
+ {%- macro format_function_declaration(tool_data) -%}
87
+ declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
88
+ {%- set params = tool_data['function']['parameters'] -%}
89
+ {%- if params -%}
90
+ ,parameters:{
91
+ {%- if params['properties'] -%}
92
+ properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
93
+ {%- endif -%}
94
+ {%- if params['required'] -%}
95
+ required:[
96
+ {%- for item in params['required'] -%}
97
+ <|"|>{{- item -}}<|"|>
98
+ {{- ',' if not loop.last -}}
99
+ {%- endfor -%}
100
+ ],
101
+ {%- endif -%}
102
+ {%- if params['type'] -%}
103
+ type:<|"|>{{- params['type'] | upper -}}<|"|>}
104
+ {%- endif -%}
105
+ {%- endif -%}
106
+ {%- if 'response' in tool_data['function'] -%}
107
+ {%- set response_declaration = tool_data['function']['response'] -%}
108
+ ,response:{
109
+ {%- if response_declaration['description'] -%}
110
+ description:<|"|>{{- response_declaration['description'] -}}<|"|>,
111
+ {%- endif -%}
112
+ {%- if response_declaration['type'] | upper == 'OBJECT' -%}
113
+ type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
114
+ {%- endif -%}
115
+ {%- endif -%}
116
+ }
117
+ {%- endmacro -%}
118
+ {%- macro format_argument(argument, escape_keys=True) -%}
119
+ {%- if argument is string -%}
120
+ {{- '<|"|>' + argument + '<|"|>' -}}
121
+ {%- elif argument is boolean -%}
122
+ {{- 'true' if argument else 'false' -}}
123
+ {%- elif argument is mapping -%}
124
+ {{- '{' -}}
125
+ {%- set ns = namespace(found_first=false) -%}
126
+ {%- for key, value in argument | dictsort -%}
127
+ {%- if ns.found_first %},{% endif -%}
128
+ {%- set ns.found_first = true -%}
129
+ {%- if escape_keys -%}
130
+ {{- '<|"|>' + key + '<|"|>' -}}
131
+ {%- else -%}
132
+ {{- key -}}
133
+ {%- endif -%}
134
+ :{{- format_argument(value, escape_keys=escape_keys) -}}
135
+ {%- endfor -%}
136
+ {{- '}' -}}
137
+ {%- elif argument is sequence -%}
138
+ {{- '[' -}}
139
+ {%- for item in argument -%}
140
+ {{- format_argument(item, escape_keys=escape_keys) -}}
141
+ {%- if not loop.last %},{% endif -%}
142
+ {%- endfor -%}
143
+ {{- ']' -}}
144
+ {%- else -%}
145
+ {{- argument -}}
146
+ {%- endif -%}
147
+ {%- endmacro -%}
148
+ {%- macro strip_thinking(text) -%}
149
+ {%- set ns = namespace(result='') -%}
150
+ {%- for part in text.split('<channel|>') -%}
151
+ {%- if '<|channel>' in part -%}
152
+ {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
153
+ {%- else -%}
154
+ {%- set ns.result = ns.result + part -%}
155
+ {%- endif -%}
156
+ {%- endfor -%}
157
+ {{- ns.result | trim -}}
158
+ {%- endmacro -%}
159
 
160
+ {%- macro format_tool_response_block(tool_name, response) -%}
161
+ {{- '<|tool_response>' -}}
162
+ {%- if response is mapping -%}
163
+ {{- 'response:' + tool_name + '{' -}}
164
+ {%- for key, value in response | dictsort -%}
165
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
166
+ {%- if not loop.last %},{% endif -%}
167
+ {%- endfor -%}
168
+ {{- '}' -}}
169
  {%- else -%}
170
+ {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
171
+ {%- endif -%}
172
+ {{- '<tool_response|>' -}}
173
+ {%- endmacro -%}
174
 
175
+ {%- set ns = namespace(prev_message_type=None) -%}
176
+ {%- set loop_messages = messages -%}
177
+ {{- bos_token -}}
178
+ {#- Handle System/Tool Definitions Block -#}
179
+ {%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
180
+ {{- '<|turn>system\n' -}}
181
+ {#- Inject Thinking token at the very top of the FIRST system turn -#}
182
+ {%- if enable_thinking is defined and enable_thinking -%}
183
+ {{- '<|think|>\n' -}}
184
+ {%- set ns.prev_message_type = 'think' -%}
185
  {%- endif -%}
186
+ {%- if messages[0]['role'] in ['system', 'developer'] -%}
187
+ {%- if messages[0]['content'] is string -%}
188
+ {{- messages[0]['content'] | trim -}}
189
+ {%- elif messages[0]['content'] is sequence -%}
190
+ {%- for item in messages[0]['content'] -%}
191
+ {{- item['text'] | trim + ' '-}}
192
+ {%- endfor -%}
193
+ {%- endif -%}
194
+ {%- set loop_messages = messages[1:] -%}
195
  {%- endif -%}
196
+ {%- if tools -%}
197
+ {%- for tool in tools %}
198
+ {{- '<|tool>' -}}
199
+ {{- format_function_declaration(tool) | trim -}}
200
+ {{- '<tool|>' -}}
201
+ {%- endfor %}
202
+ {%- set ns.prev_message_type = 'tool' -%}
203
+ {%- endif -%}
204
+ {{- '<turn|>\n' -}}
205
+ {%- endif %}
206
+
207
+ {#- Pre-scan: find last user message index for reasoning guard -#}
208
+ {%- set ns_turn = namespace(last_user_idx=-1) -%}
209
+ {%- for i in range(loop_messages | length) -%}
210
+ {%- if loop_messages[i]['role'] == 'user' -%}
211
+ {%- set ns_turn.last_user_idx = i -%}
212
+ {%- endif -%}
213
+ {%- endfor -%}
214
+
215
+ {#- Loop through messages -#}
216
+ {%- for message in loop_messages -%}
217
+ {%- if message['role'] != 'tool' -%}
218
+ {%- set ns.prev_message_type = None -%}
219
+ {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
220
+ {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
221
+ {%- set prev_nt = namespace(role=None, found=false) -%}
222
+ {%- if loop.index0 > 0 -%}
223
+ {%- for j in range(loop.index0 - 1, -1, -1) -%}
224
+ {%- if not prev_nt.found -%}
225
+ {%- if loop_messages[j]['role'] != 'tool' -%}
226
+ {%- set prev_nt.role = loop_messages[j]['role'] -%}
227
+ {%- set prev_nt.found = true -%}
228
+ {%- endif -%}
229
  {%- endif -%}
230
  {%- endfor -%}
 
 
231
  {%- endif -%}
232
+ {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
233
+ {%- if not continue_same_model_turn -%}
234
+ {{- '<|turn>' + role + '\n' }}
235
+ {%- endif -%}
236
+
237
+ {#- Render reasoning/reasoning_content as thinking channel -#}
238
+ {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
239
+ {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
240
+ {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
241
+ {%- endif -%}
242
+
243
+ {%- if message['tool_calls'] -%}
244
+ {%- for tool_call in message['tool_calls'] -%}
245
+ {%- set function = tool_call['function'] -%}
246
+ {{- '<|tool_call>call:' + function['name'] + '{' -}}
247
+ {%- if function['arguments'] is mapping -%}
248
+ {%- set ns_args = namespace(found_first=false) -%}
249
+ {%- for key, value in function['arguments'] | dictsort -%}
250
+ {%- if ns_args.found_first %},{% endif -%}
251
+ {%- set ns_args.found_first = true -%}
252
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
253
+ {%- endfor -%}
254
+ {%- elif function['arguments'] is string -%}
255
+ {{- function['arguments'] -}}
256
+ {%- endif -%}
257
+ {{- '}<tool_call|>' -}}
258
+ {%- endfor -%}
259
+ {%- set ns.prev_message_type = 'tool_call' -%}
260
+ {%- endif -%}
261
+
262
+ {%- set ns_tr_out = namespace(flag=false) -%}
263
+ {%- if message.get('tool_responses') -%}
264
+ {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
265
+ {%- for tool_response in message['tool_responses'] -%}
266
+ {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
267
+ {%- set ns_tr_out.flag = true -%}
268
+ {%- set ns.prev_message_type = 'tool_response' -%}
269
+ {%- endfor -%}
270
+ {%- elif message.get('tool_calls') -%}
271
+ {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
272
+ {%- set ns_tool_scan = namespace(stopped=false) -%}
273
+ {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
274
+ {%- if ns_tool_scan.stopped -%}
275
+ {%- elif loop_messages[k]['role'] != 'tool' -%}
276
+ {%- set ns_tool_scan.stopped = true -%}
277
+ {%- else -%}
278
+ {%- set follow = loop_messages[k] -%}
279
+ {#- Resolve tool_call_id to function name -#}
280
+ {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
281
+ {%- for tc in message['tool_calls'] -%}
282
+ {%- if tc.get('id') == follow.get('tool_call_id') -%}
283
+ {%- set ns_tname.name = tc['function']['name'] -%}
284
+ {%- endif -%}
285
+ {%- endfor -%}
286
+ {#- Handle content as string or content-parts array -#}
287
+ {%- set tool_body = follow.get('content') -%}
288
+ {%- if tool_body is string -%}
289
+ {{- format_tool_response_block(ns_tname.name, tool_body) -}}
290
+ {%- elif tool_body is sequence and tool_body is not string -%}
291
+ {%- set ns_txt = namespace(s='') -%}
292
+ {%- for part in tool_body -%}
293
+ {%- if part.get('type') == 'text' -%}
294
+ {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
295
+ {%- endif -%}
296
+ {%- endfor -%}
297
+ {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
298
+ {%- for part in tool_body -%}
299
+ {%- if part.get('type') == 'image' -%}
300
+ {{- '<|image|>' -}}
301
+ {%- elif part.get('type') == 'audio' -%}
302
+ {{- '<|audio|>' -}}
303
+ {%- elif part.get('type') == 'video' -%}
304
+ {{- '<|video|>' -}}
305
+ {%- endif -%}
306
+ {%- endfor -%}
307
+ {%- else -%}
308
+ {{- format_tool_response_block(ns_tname.name, tool_body) -}}
309
+ {%- endif -%}
310
+ {%- set ns_tr_out.flag = true -%}
311
+ {%- set ns.prev_message_type = 'tool_response' -%}
312
+ {%- endif -%}
313
+ {%- endfor -%}
314
+ {%- endif -%}
315
+
316
+ {%- set captured_content -%}
317
+ {%- if message['content'] is string -%}
318
+ {%- if role == 'model' -%}
319
+ {{- strip_thinking(message['content']) -}}
320
+ {%- else -%}
321
+ {{- message['content'] | trim -}}
322
+ {%- endif -%}
323
+ {%- elif message['content'] is sequence -%}
324
+ {%- for item in message['content'] -%}
325
+ {%- if item['type'] == 'text' -%}
326
+ {%- if role == 'model' -%}
327
+ {{- strip_thinking(item['text']) -}}
328
+ {%- else -%}
329
+ {{- item['text'] | trim -}}
330
+ {%- endif -%}
331
+ {%- elif item['type'] == 'image' -%}
332
+ {{- '<|image|>' -}}
333
+ {%- set ns.prev_message_type = 'image' -%}
334
+ {%- elif item['type'] == 'audio' -%}
335
+ {{- '<|audio|>' -}}
336
+ {%- set ns.prev_message_type = 'audio' -%}
337
+ {%- elif item['type'] == 'video' -%}
338
+ {{- '<|video|>' -}}
339
+ {%- set ns.prev_message_type = 'video' -%}
340
+ {%- endif -%}
341
+ {%- endfor -%}
342
+ {%- endif -%}
343
+ {%- endset -%}
344
+
345
+ {{- captured_content -}}
346
+ {%- set has_content = captured_content | trim | length > 0 -%}
347
+
348
+ {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
349
+ {{- '<|tool_response>' -}}
350
+ {%- elif not (ns_tr_out.flag and not has_content) -%}
351
+ {{- '<turn|>\n' -}}
352
+ {%- endif -%}
353
+ {%- endif -%}
354
  {%- endfor -%}
355
+
356
  {%- if add_generation_prompt -%}
357
+ {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
358
+ {{- '<|turn>model\n' -}}
359
+ {%- endif -%}
360
+ {%- endif -%}
processor_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_ms_per_token": 40,
3
+ "audio_seq_length": 750,
4
+ "feature_extractor": {
5
+ "dither": 0.0,
6
+ "feature_extractor_type": "Gemma4AudioFeatureExtractor",
7
+ "feature_size": 128,
8
+ "fft_length": 512,
9
+ "fft_overdrive": false,
10
+ "frame_length": 320,
11
+ "hop_length": 160,
12
+ "input_scale_factor": 1.0,
13
+ "max_frequency": 8000.0,
14
+ "mel_floor": 0.001,
15
+ "min_frequency": 0.0,
16
+ "padding_side": "right",
17
+ "padding_value": 0.0,
18
+ "per_bin_mean": null,
19
+ "per_bin_stddev": null,
20
+ "preemphasis": 0.0,
21
+ "preemphasis_htk_flavor": true,
22
+ "return_attention_mask": true,
23
+ "sampling_rate": 16000
24
+ },
25
+ "image_processor": {
26
+ "do_convert_rgb": true,
27
+ "do_normalize": false,
28
+ "do_rescale": true,
29
+ "do_resize": true,
30
+ "image_mean": [
31
+ 0.0,
32
+ 0.0,
33
+ 0.0
34
+ ],
35
+ "image_processor_type": "Gemma4ImageProcessor",
36
+ "image_seq_length": 280,
37
+ "image_std": [
38
+ 1.0,
39
+ 1.0,
40
+ 1.0
41
+ ],
42
+ "max_soft_tokens": 280,
43
+ "patch_size": 16,
44
+ "pooling_kernel_size": 3,
45
+ "resample": 3,
46
+ "rescale_factor": 0.00392156862745098
47
+ },
48
+ "image_seq_length": 280,
49
+ "processor_class": "Gemma4Processor",
50
+ "video_processor": {
51
+ "do_convert_rgb": true,
52
+ "do_normalize": true,
53
+ "do_rescale": true,
54
+ "do_resize": true,
55
+ "do_sample_frames": true,
56
+ "image_mean": [
57
+ 0.0,
58
+ 0.0,
59
+ 0.0
60
+ ],
61
+ "image_std": [
62
+ 1.0,
63
+ 1.0,
64
+ 1.0
65
+ ],
66
+ "max_soft_tokens": 70,
67
+ "num_frames": 32,
68
+ "patch_size": 16,
69
+ "pooling_kernel_size": 3,
70
+ "resample": 3,
71
+ "rescale_factor": 0.00392156862745098,
72
+ "return_metadata": false,
73
+ "video_processor_type": "Gemma4VideoProcessor"
74
+ }
75
+ }
runs/Jun19_01-37-19_ffa1dd7a1058/events.out.tfevents.1781833039.ffa1dd7a1058.109416.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b13629456fa2eec230df3b7e1b0a8cf0f9140204ba2a3b9b0832c83c5c0fd9a
3
+ size 8280
runs/Jun19_01-41-08_ffa1dd7a1058/events.out.tfevents.1781833268.ffa1dd7a1058.112980.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f4c5491ec12781d2e8030b98be40b47f6274f51c717914ea34716ab410ebd6
3
+ size 47867
runs/Jun19_02-29-14_ffa1dd7a1058/events.out.tfevents.1781836154.ffa1dd7a1058.125401.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a3980de2b8aa85fe6a6ff2e9a83e15f5f70d1b85ab553755a0c0783525d243
3
+ size 48306
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
- size 33384568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2619fe11b50dbed06ac443c51d757b354d0b62d64baa514404d4e84e6713519
3
+ size 32169780
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09e0961226ac78e88a3bed5f714c861553680990bcec8236ad22da2b8f0ce954
3
- size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb8ad83ae314943a7798362b2c17714f99d8eb27b9a9bf374d8f3ea9349784e
3
+ size 5713