galeswel commited on
Commit
bf6f0cf
·
verified ·
1 Parent(s): 34f18c2

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -1,35 +1,17 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz 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
 
1
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
2
+ adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
3
+ pytorch_model_fsdp.bin filter=lfs diff=lfs merge=lfs -text
4
+ model-00013-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
5
+ model-00011-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
6
+ model-00004-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
7
+ model-00003-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
8
+ model-00002-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
9
+ model-00001-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
10
+ model-00006-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
11
+ model-00005-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
12
+ model-00008-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
13
+ model-00007-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
14
+ model-00009-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
15
+ model-00012-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
16
+ model-00010-of-00013.safetensors filter=lfs diff=lfs merge=lfs -text
17
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: coder3101/gemma-4-31B-it-heretic
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:coder3101/gemma-4-31B-it-heretic
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.19.1
chat_template.jinja ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- set add_comma = false -%}
6
+ {%- if 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([])) -}}
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
+ {%- macro format_tool_response_block(tool_name, response) -%}
160
+ {{- '<|tool_response>' -}}
161
+ {%- if response is mapping -%}
162
+ {{- 'response:' + tool_name + '{' -}}
163
+ {%- for key, value in response | dictsort -%}
164
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
165
+ {%- if not loop.last %},{% endif -%}
166
+ {%- endfor -%}
167
+ {{- '}' -}}
168
+ {%- else -%}
169
+ {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
170
+ {%- endif -%}
171
+ {{- '<tool_response|>' -}}
172
+ {%- endmacro -%}
173
+ {%- set ns = namespace(prev_message_type=None) -%}
174
+ {%- set loop_messages = messages -%}
175
+ {{- bos_token -}}
176
+ {#- Handle System/Tool Definitions Block -#}
177
+ {%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
178
+ {{- '<|turn>system\n' -}}
179
+ {#- Inject Thinking token at the very top of the FIRST system turn -#}
180
+ {%- if enable_thinking is defined and enable_thinking -%}
181
+ {{- '<|think|>\n' -}}
182
+ {%- set ns.prev_message_type = 'think' -%}
183
+ {%- endif -%}
184
+ {%- if messages[0]['role'] in ['system', 'developer'] -%}
185
+ {{- messages[0]['content'] | trim -}}
186
+ {%- set loop_messages = messages[1:] -%}
187
+ {%- endif -%}
188
+ {%- if tools -%}
189
+ {%- for tool in tools %}
190
+ {{- '<|tool>' -}}
191
+ {{- format_function_declaration(tool) | trim -}}
192
+ {{- '<tool|>' -}}
193
+ {%- endfor %}
194
+ {%- set ns.prev_message_type = 'tool' -%}
195
+ {%- endif -%}
196
+ {{- '<turn|>\n' -}}
197
+ {%- endif %}
198
+ {#- Pre-scan: find last user message index for reasoning guard -#}
199
+ {%- set ns_turn = namespace(last_user_idx=-1) -%}
200
+ {%- for i in range(loop_messages | length) -%}
201
+ {%- if loop_messages[i]['role'] == 'user' -%}
202
+ {%- set ns_turn.last_user_idx = i -%}
203
+ {%- endif -%}
204
+ {%- endfor -%}
205
+ {#- Loop through messages -#}
206
+ {%- for message in loop_messages -%}
207
+ {%- if message['role'] != 'tool' -%}
208
+ {%- set ns.prev_message_type = None -%}
209
+ {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
210
+ {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
211
+ {%- set prev_nt = namespace(role=None, found=false) -%}
212
+ {%- if loop.index0 > 0 -%}
213
+ {%- for j in range(loop.index0 - 1, -1, -1) -%}
214
+ {%- if not prev_nt.found -%}
215
+ {%- if loop_messages[j]['role'] != 'tool' -%}
216
+ {%- set prev_nt.role = loop_messages[j]['role'] -%}
217
+ {%- set prev_nt.found = true -%}
218
+ {%- endif -%}
219
+ {%- endif -%}
220
+ {%- endfor -%}
221
+ {%- endif -%}
222
+ {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
223
+ {%- if not continue_same_model_turn -%}
224
+ {{- '<|turn>' + role + '\n' }}
225
+ {%- endif -%}
226
+ {#- Render reasoning/reasoning_content as thinking channel -#}
227
+ {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
228
+ {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
229
+ {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
230
+ {%- endif -%}
231
+ {%- if message['tool_calls'] -%}
232
+ {%- for tool_call in message['tool_calls'] -%}
233
+ {%- set function = tool_call['function'] -%}
234
+ {{- '<|tool_call>call:' + function['name'] + '{' -}}
235
+ {%- if function['arguments'] is mapping -%}
236
+ {%- set ns_args = namespace(found_first=false) -%}
237
+ {%- for key, value in function['arguments'] | dictsort -%}
238
+ {%- if ns_args.found_first %},{% endif -%}
239
+ {%- set ns_args.found_first = true -%}
240
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
241
+ {%- endfor -%}
242
+ {%- elif function['arguments'] is string -%}
243
+ {{- function['arguments'] -}}
244
+ {%- endif -%}
245
+ {{- '}<tool_call|>' -}}
246
+ {%- endfor -%}
247
+ {%- set ns.prev_message_type = 'tool_call' -%}
248
+ {%- endif -%}
249
+ {%- set ns_tr_out = namespace(flag=false) -%}
250
+ {%- if message.get('tool_responses') -%}
251
+ {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
252
+ {%- for tool_response in message['tool_responses'] -%}
253
+ {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
254
+ {%- set ns_tr_out.flag = true -%}
255
+ {%- set ns.prev_message_type = 'tool_response' -%}
256
+ {%- endfor -%}
257
+ {%- elif message.get('tool_calls') -%}
258
+ {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
259
+ {%- set ns_tool_scan = namespace(stopped=false) -%}
260
+ {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
261
+ {%- if ns_tool_scan.stopped -%}
262
+ {%- elif loop_messages[k]['role'] != 'tool' -%}
263
+ {%- set ns_tool_scan.stopped = true -%}
264
+ {%- else -%}
265
+ {%- set follow = loop_messages[k] -%}
266
+ {#- Resolve tool_call_id to function name -#}
267
+ {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
268
+ {%- for tc in message['tool_calls'] -%}
269
+ {%- if tc.get('id') == follow.get('tool_call_id') -%}
270
+ {%- set ns_tname.name = tc['function']['name'] -%}
271
+ {%- endif -%}
272
+ {%- endfor -%}
273
+ {#- Handle content as string or content-parts array -#}
274
+ {%- set tool_body = follow.get('content') -%}
275
+ {%- if tool_body is string -%}
276
+ {{- format_tool_response_block(ns_tname.name, tool_body) -}}
277
+ {%- elif tool_body is sequence and tool_body is not string -%}
278
+ {%- set ns_txt = namespace(s='') -%}
279
+ {%- for part in tool_body -%}
280
+ {%- if part.get('type') == 'text' -%}
281
+ {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
282
+ {%- endif -%}
283
+ {%- endfor -%}
284
+ {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
285
+ {%- else -%}
286
+ {{- format_tool_response_block(ns_tname.name, tool_body) -}}
287
+ {%- endif -%}
288
+ {%- set ns_tr_out.flag = true -%}
289
+ {%- set ns.prev_message_type = 'tool_response' -%}
290
+ {%- endif -%}
291
+ {%- endfor -%}
292
+ {%- endif -%}
293
+ {%- if message['content'] is string -%}
294
+ {%- if role == 'model' -%}
295
+ {{- strip_thinking(message['content']) -}}
296
+ {%- else -%}
297
+ {{- message['content'] | trim -}}
298
+ {%- endif -%}
299
+ {%- elif message['content'] is sequence -%}
300
+ {%- for item in message['content'] -%}
301
+ {%- if item['type'] == 'text' -%}
302
+ {%- if role == 'model' -%}
303
+ {{- strip_thinking(item['text']) -}}
304
+ {%- else -%}
305
+ {{- item['text'] | trim -}}
306
+ {%- endif -%}
307
+ {%- elif item['type'] == 'image' -%}
308
+ {{- '<|image|>' -}}
309
+ {%- set ns.prev_message_type = 'image' -%}
310
+ {%- elif item['type'] == 'audio' -%}
311
+ {{- '<|audio|>' -}}
312
+ {%- set ns.prev_message_type = 'audio' -%}
313
+ {%- elif item['type'] == 'video' -%}
314
+ {{- '<|video|>' -}}
315
+ {%- set ns.prev_message_type = 'video' -%}
316
+ {%- endif -%}
317
+ {%- endfor -%}
318
+ {%- endif -%}
319
+ {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
320
+ {{- '<|tool_response>' -}}
321
+ {%- elif not (ns_tr_out.flag and not message.get('content')) -%}
322
+ {{- '<turn|>\n' -}}
323
+ {%- endif -%}
324
+ {%- endif -%}
325
+ {%- endfor -%}
326
+ {%- if add_generation_prompt -%}
327
+ {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
328
+ {{- '<|turn>model\n' -}}
329
+ {%- if not enable_thinking | default(false) -%}
330
+ {{- '<|channel>thought\n<channel|>' -}}
331
+ {%- endif -%}
332
+ {%- endif -%}
333
+ {%- endif -%}
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{%- macro format_parameters(properties, required) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([])) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking is defined and enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages[0]['role'] in ['system', 'developer'] -%}\n {{- messages[0]['content'] | trim -}}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n {%- set prev_nt = namespace(role=None, found=false) -%}\n {%- if loop.index0 > 0 -%}\n {%- for j in range(loop.index0 - 1, -1, -1) -%}\n {%- if not prev_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set prev_nt.role = loop_messages[j]['role'] -%}\n {%- set prev_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n {%- if message['tool_calls'] -%}\n {%- for tool_call in message['tool_calls'] -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is string -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message['tool_responses'] -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n {%- for tc in message['tool_calls'] -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if message['content'] is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message['content'] is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item['type'] == 'image' -%}\n {{- '<|image|>' -}}\n {%- set ns.prev_message_type = 'image' -%}\n {%- elif item['type'] == 'audio' -%}\n {{- '<|audio|>' -}}\n {%- set ns.prev_message_type = 'audio' -%}\n {%- elif item['type'] == 'video' -%}\n {{- '<|video|>' -}}\n {%- set ns.prev_message_type = 'video' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif not (ns_tr_out.flag and not message.get('content')) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- if not enable_thinking | default(false) -%}\n {{- '<|channel>thought\\n<channel|>' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endif -%}"
3
+ }
config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": null,
6
+ "audio_token_id": 258881,
7
+ "boa_token_id": 256000,
8
+ "boi_token_id": 255999,
9
+ "dtype": "bfloat16",
10
+ "eoa_token_id": 258883,
11
+ "eoa_token_index": 258883,
12
+ "eoi_token_id": 258882,
13
+ "eos_token_id": [
14
+ 1,
15
+ 106
16
+ ],
17
+ "image_token_id": 258880,
18
+ "initializer_range": 0.02,
19
+ "model_type": "gemma4",
20
+ "text_config": {
21
+ "attention_bias": false,
22
+ "attention_dropout": 0.0,
23
+ "attention_k_eq_v": true,
24
+ "bos_token_id": 2,
25
+ "dtype": "bfloat16",
26
+ "enable_moe_block": false,
27
+ "eos_token_id": 1,
28
+ "expert_intermediate_size": null,
29
+ "final_logit_softcapping": 30.0,
30
+ "global_head_dim": 512,
31
+ "head_dim": 256,
32
+ "hidden_activation": "gelu_pytorch_tanh",
33
+ "hidden_size": 5376,
34
+ "hidden_size_per_layer_input": 0,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 21504,
37
+ "layer_types": [
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "full_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "full_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "full_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "full_attention"
98
+ ],
99
+ "max_position_embeddings": 262144,
100
+ "model_type": "gemma4_text",
101
+ "moe_intermediate_size": null,
102
+ "num_attention_heads": 32,
103
+ "num_experts": null,
104
+ "num_global_key_value_heads": 4,
105
+ "num_hidden_layers": 60,
106
+ "num_key_value_heads": 16,
107
+ "num_kv_shared_layers": 0,
108
+ "pad_token_id": 0,
109
+ "rms_norm_eps": 1e-06,
110
+ "rope_parameters": {
111
+ "full_attention": {
112
+ "partial_rotary_factor": 0.25,
113
+ "rope_theta": 1000000.0,
114
+ "rope_type": "proportional"
115
+ },
116
+ "sliding_attention": {
117
+ "rope_theta": 10000.0,
118
+ "rope_type": "default"
119
+ }
120
+ },
121
+ "sliding_window": 1024,
122
+ "tie_word_embeddings": true,
123
+ "top_k_experts": null,
124
+ "use_bidirectional_attention": "vision",
125
+ "use_cache": true,
126
+ "use_double_wide_mlp": false,
127
+ "vocab_size": 262144,
128
+ "vocab_size_per_layer_input": 262144
129
+ },
130
+ "tie_word_embeddings": true,
131
+ "transformers_version": "5.5.0.dev0",
132
+ "video_token_id": 258884,
133
+ "vision_config": {
134
+ "_name_or_path": "",
135
+ "architectures": null,
136
+ "attention_bias": false,
137
+ "attention_dropout": 0.0,
138
+ "chunk_size_feed_forward": 0,
139
+ "default_output_length": 280,
140
+ "dtype": "bfloat16",
141
+ "global_head_dim": 72,
142
+ "head_dim": 72,
143
+ "hidden_activation": "gelu_pytorch_tanh",
144
+ "hidden_size": 1152,
145
+ "id2label": {
146
+ "0": "LABEL_0",
147
+ "1": "LABEL_1"
148
+ },
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4304,
151
+ "is_encoder_decoder": false,
152
+ "label2id": {
153
+ "LABEL_0": 0,
154
+ "LABEL_1": 1
155
+ },
156
+ "max_position_embeddings": 131072,
157
+ "model_type": "gemma4_vision",
158
+ "num_attention_heads": 16,
159
+ "num_hidden_layers": 27,
160
+ "num_key_value_heads": 16,
161
+ "output_attentions": false,
162
+ "output_hidden_states": false,
163
+ "patch_size": 16,
164
+ "pooling_kernel_size": 3,
165
+ "position_embedding_size": 10240,
166
+ "problem_type": null,
167
+ "return_dict": true,
168
+ "rms_norm_eps": 1e-06,
169
+ "rope_parameters": {
170
+ "rope_theta": 100.0,
171
+ "rope_type": "default"
172
+ },
173
+ "standardize": true,
174
+ "use_clipped_linears": false
175
+ },
176
+ "vision_soft_tokens_per_image": 280
177
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106,
7
+ 50
8
+ ],
9
+ "pad_token_id": 0,
10
+ "temperature": 1.0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "5.5.0.dev0"
14
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9a05d0140b1ba3212a1a497443442534ead751a1222c3198ab2e4b11e62328
3
+ size 5209232190
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1258f81915c29b7fa49286df9c341d8f75c9d2e18b43a51bd570e34220f86010
3
+ size 5130912714
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748fa5c9036dc068f2719afd36ce0147a88a72134b047d2936397781043832a6
3
+ size 5031855666
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0aadb0d454aea0d46801c2ff7c8f2185c0f21b17a72f5bdd8d9bd830865147f
3
+ size 5031823034
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348aae23246c7eb2e8cb926dd0deeb86ffe35053406ef0ef39915057bcfaea6d
3
+ size 5130923684
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265a1b305afd27e14abff7c14034e4330d410a7226c9b264fb2ff3b94013b2e6
3
+ size 5020811330
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbfa0e7330baf685da36ac9ab7df72726fa26324ab0b705f7c56331faec5f761
3
+ size 5130912714
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df2c4801e8ed36039a42f257243c1d72a7fc6315f438e750287d17e33d11ec8
3
+ size 5031855666
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145b391be0d75393e3c94d45f4d8d6ab211b232db513620f6e3b419021793e38
3
+ size 5020823580
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8799720b8e6651107fcb668debc9d31bdad24beabb7eed547536fa7c877087a7
3
+ size 5141923098
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ffe870193ee24bc1a79ae04640b0e0417f6e500828b9e0c030349b65d03d56a
3
+ size 5130912714
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49ec7483bf3dacbbf1c4bbdbd06b3fd6a60a2302ac8bdcbd436cb4dfc6249af
3
+ size 5020811338
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da95d8eceb1598f63e778c22ed0941de8f0f52da8c1c34e38009a076b1409fc
3
+ size 1513538152
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_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
+ }
pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e959e43a4d9498dcb93a7cc8cdf189f7da6e1e67a9e0c7fdc1296b1a3ecdd826
3
+ size 1959190293
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
+ size 32169626
tokenizer_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|audio|>",
3
+ "backend": "tokenizers",
4
+ "boa_token": "<|audio>",
5
+ "boi_token": "<|image>",
6
+ "bos_token": "<bos>",
7
+ "eoa_token": "<audio|>",
8
+ "eoc_token": "<channel|>",
9
+ "eoi_token": "<image|>",
10
+ "eos_token": "<eos>",
11
+ "eot_token": "<turn|>",
12
+ "escape_token": "<|\"|>",
13
+ "etc_token": "<tool_call|>",
14
+ "etd_token": "<tool|>",
15
+ "etr_token": "<tool_response|>",
16
+ "extra_special_tokens": [
17
+ "<|video|>"
18
+ ],
19
+ "image_token": "<|image|>",
20
+ "is_local": false,
21
+ "local_files_only": false,
22
+ "mask_token": "<mask>",
23
+ "model_max_length": 1000000000000000019884624838656,
24
+ "model_specific_special_tokens": {
25
+ "audio_token": "<|audio|>",
26
+ "boa_token": "<|audio>",
27
+ "boi_token": "<|image>",
28
+ "eoa_token": "<audio|>",
29
+ "eoc_token": "<channel|>",
30
+ "eoi_token": "<image|>",
31
+ "eot_token": "<turn|>",
32
+ "escape_token": "<|\"|>",
33
+ "etc_token": "<tool_call|>",
34
+ "etd_token": "<tool|>",
35
+ "etr_token": "<tool_response|>",
36
+ "image_token": "<|image|>",
37
+ "soc_token": "<|channel>",
38
+ "sot_token": "<|turn>",
39
+ "stc_token": "<|tool_call>",
40
+ "std_token": "<|tool>",
41
+ "str_token": "<|tool_response>",
42
+ "think_token": "<|think|>"
43
+ },
44
+ "pad_token": "<pad>",
45
+ "padding_side": "left",
46
+ "processor_class": "Gemma4Processor",
47
+ "response_schema": {
48
+ "properties": {
49
+ "content": {
50
+ "type": "string"
51
+ },
52
+ "role": {
53
+ "const": "assistant"
54
+ },
55
+ "thinking": {
56
+ "type": "string"
57
+ },
58
+ "tool_calls": {
59
+ "items": {
60
+ "properties": {
61
+ "function": {
62
+ "properties": {
63
+ "arguments": {
64
+ "additionalProperties": {},
65
+ "type": "object",
66
+ "x-parser": "gemma4-tool-call"
67
+ },
68
+ "name": {
69
+ "type": "string"
70
+ }
71
+ },
72
+ "type": "object",
73
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
74
+ },
75
+ "type": {
76
+ "const": "function"
77
+ }
78
+ },
79
+ "type": "object"
80
+ },
81
+ "type": "array",
82
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
83
+ }
84
+ },
85
+ "type": "object",
86
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
87
+ },
88
+ "soc_token": "<|channel>",
89
+ "sot_token": "<|turn>",
90
+ "stc_token": "<|tool_call>",
91
+ "std_token": "<|tool>",
92
+ "str_token": "<|tool_response>",
93
+ "think_token": "<|think|>",
94
+ "tokenizer_class": "GemmaTokenizer",
95
+ "unk_token": "<unk>",
96
+ "chat_template": "{%- macro format_parameters(properties, required) -%}\n {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in properties | dictsort -%}\n {%- set add_comma = false -%}\n {%- if key not in standard_keys -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {{ key }}:{\n {%- if value['description'] -%}\n description:<|\"|>{{ value['description'] }}<|\"|>\n {%- set add_comma = true -%}\n {%- endif -%}\n {%- if value['type'] | upper == 'STRING' -%}\n {%- if value['enum'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n enum:{{ format_argument(value['enum']) }}\n {%- endif -%}\n {%- elif value['type'] | upper == 'ARRAY' -%}\n {%- if value['items'] is mapping and value['items'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n items:{\n {%- set ns_items = namespace(found_first=false) -%}\n {%- for item_key, item_value in value['items'] | dictsort -%}\n {%- if item_value is not none -%}\n {%- if ns_items.found_first %},{% endif -%}\n {%- set ns_items.found_first = true -%}\n {%- if item_key == 'properties' -%}\n properties:{\n {%- if item_value is mapping -%}\n {{- format_parameters(item_value, value['items']['required'] | default([])) -}}\n {%- endif -%}\n }\n {%- elif item_key == 'required' -%}\n required:[\n {%- for req_item in item_value -%}\n <|\"|>{{- req_item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- elif item_key == 'type' -%}\n {%- if item_value is string -%}\n type:{{ format_argument(item_value | upper) }}\n {%- else -%}\n type:{{ format_argument(item_value | map('upper') | list) }}\n {%- endif -%}\n {%- else -%}\n {{ item_key }}:{{ format_argument(item_value) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n }\n {%- endif -%}\n {%- endif -%}\n {%- if value['nullable'] %}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n nullable:true\n {%- endif -%}\n {%- if value['type'] | upper == 'OBJECT' -%}\n {%- if value['properties'] is defined and value['properties'] is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value['properties'], value['required'] | default([])) -}}\n }\n {%- elif value is mapping -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n properties:{\n {{- format_parameters(value, value['required'] | default([])) -}}\n }\n {%- endif -%}\n {%- if value['required'] -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n required:[\n {%- for item in value['required'] | default([]) -%}\n <|\"|>{{- item -}}<|\"|>\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n ]\n {%- endif -%}\n {%- endif -%}\n {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}\n type:<|\"|>{{ value['type'] | upper }}<|\"|>}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n{%- macro format_function_declaration(tool_data) -%}\n declaration:{{- tool_data['function']['name'] -}}{description:<|\"|>{{- tool_data['function']['description'] -}}<|\"|>\n {%- set params = tool_data['function']['parameters'] -%}\n {%- if params -%}\n ,parameters:{\n {%- if params['properties'] -%}\n properties:{ {{- format_parameters(params['properties'], params['required']) -}} },\n {%- endif -%}\n {%- if params['required'] -%}\n required:[\n {%- for item in params['required'] -%}\n <|\"|>{{- item -}}<|\"|>\n {{- ',' if not loop.last -}}\n {%- endfor -%}\n ],\n {%- endif -%}\n {%- if params['type'] -%}\n type:<|\"|>{{- params['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n {%- if 'response' in tool_data['function'] -%}\n {%- set response_declaration = tool_data['function']['response'] -%}\n ,response:{\n {%- if response_declaration['description'] -%}\n description:<|\"|>{{- response_declaration['description'] -}}<|\"|>,\n {%- endif -%}\n {%- if response_declaration['type'] | upper == 'OBJECT' -%}\n type:<|\"|>{{- response_declaration['type'] | upper -}}<|\"|>}\n {%- endif -%}\n {%- endif -%}\n }\n{%- endmacro -%}\n{%- macro format_argument(argument, escape_keys=True) -%}\n {%- if argument is string -%}\n {{- '<|\"|>' + argument + '<|\"|>' -}}\n {%- elif argument is boolean -%}\n {{- 'true' if argument else 'false' -}}\n {%- elif argument is mapping -%}\n {{- '{' -}}\n {%- set ns = namespace(found_first=false) -%}\n {%- for key, value in argument | dictsort -%}\n {%- if ns.found_first %},{% endif -%}\n {%- set ns.found_first = true -%}\n {%- if escape_keys -%}\n {{- '<|\"|>' + key + '<|\"|>' -}}\n {%- else -%}\n {{- key -}}\n {%- endif -%}\n :{{- format_argument(value, escape_keys=escape_keys) -}}\n {%- endfor -%}\n {{- '}' -}}\n {%- elif argument is sequence -%}\n {{- '[' -}}\n {%- for item in argument -%}\n {{- format_argument(item, escape_keys=escape_keys) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- ']' -}}\n {%- else -%}\n {{- argument -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n{%- macro format_tool_response_block(tool_name, response) -%}\n {{- '<|tool_response>' -}}\n {%- if response is mapping -%}\n {{- 'response:' + tool_name + '{' -}}\n {%- for key, value in response | dictsort -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- if not loop.last %},{% endif -%}\n {%- endfor -%}\n {{- '}' -}}\n {%- else -%}\n {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}\n {%- endif -%}\n {{- '<tool_response|>' -}}\n{%- endmacro -%}\n{%- set ns = namespace(prev_message_type=None) -%}\n{%- set loop_messages = messages -%}\n{{- bos_token -}}\n{#- Handle System/Tool Definitions Block -#}\n{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}\n {{- '<|turn>system\\n' -}}\n {#- Inject Thinking token at the very top of the FIRST system turn -#}\n {%- if enable_thinking is defined and enable_thinking -%}\n {{- '<|think|>\\n' -}}\n {%- set ns.prev_message_type = 'think' -%}\n {%- endif -%}\n {%- if messages[0]['role'] in ['system', 'developer'] -%}\n {{- messages[0]['content'] | trim -}}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {%- if tools -%}\n {%- for tool in tools %}\n {{- '<|tool>' -}}\n {{- format_function_declaration(tool) | trim -}}\n {{- '<tool|>' -}}\n {%- endfor %}\n {%- set ns.prev_message_type = 'tool' -%}\n {%- endif -%}\n {{- '<turn|>\\n' -}}\n{%- endif %}\n{#- Pre-scan: find last user message index for reasoning guard -#}\n{%- set ns_turn = namespace(last_user_idx=-1) -%}\n{%- for i in range(loop_messages | length) -%}\n {%- if loop_messages[i]['role'] == 'user' -%}\n {%- set ns_turn.last_user_idx = i -%}\n {%- endif -%}\n{%- endfor -%}\n{#- Loop through messages -#}\n{%- for message in loop_messages -%}\n {%- if message['role'] != 'tool' -%}\n {%- set ns.prev_message_type = None -%}\n {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}\n {#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}\n {%- set prev_nt = namespace(role=None, found=false) -%}\n {%- if loop.index0 > 0 -%}\n {%- for j in range(loop.index0 - 1, -1, -1) -%}\n {%- if not prev_nt.found -%}\n {%- if loop_messages[j]['role'] != 'tool' -%}\n {%- set prev_nt.role = loop_messages[j]['role'] -%}\n {%- set prev_nt.found = true -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}\n {%- if not continue_same_model_turn -%}\n {{- '<|turn>' + role + '\\n' }}\n {%- endif -%}\n {#- Render reasoning/reasoning_content as thinking channel -#}\n {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}\n {%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}\n {{- '<|channel>thought\\n' + thinking_text + '\\n<channel|>' -}}\n {%- endif -%}\n {%- if message['tool_calls'] -%}\n {%- for tool_call in message['tool_calls'] -%}\n {%- set function = tool_call['function'] -%}\n {{- '<|tool_call>call:' + function['name'] + '{' -}}\n {%- if function['arguments'] is mapping -%}\n {%- set ns_args = namespace(found_first=false) -%}\n {%- for key, value in function['arguments'] | dictsort -%}\n {%- if ns_args.found_first %},{% endif -%}\n {%- set ns_args.found_first = true -%}\n {{- key -}}:{{- format_argument(value, escape_keys=False) -}}\n {%- endfor -%}\n {%- elif function['arguments'] is string -%}\n {{- function['arguments'] -}}\n {%- endif -%}\n {{- '}<tool_call|>' -}}\n {%- endfor -%}\n {%- set ns.prev_message_type = 'tool_call' -%}\n {%- endif -%}\n {%- set ns_tr_out = namespace(flag=false) -%}\n {%- if message.get('tool_responses') -%}\n {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}\n {%- for tool_response in message['tool_responses'] -%}\n {{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endfor -%}\n {%- elif message.get('tool_calls') -%}\n {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}\n {%- set ns_tool_scan = namespace(stopped=false) -%}\n {%- for k in range(loop.index0 + 1, loop_messages | length) -%}\n {%- if ns_tool_scan.stopped -%}\n {%- elif loop_messages[k]['role'] != 'tool' -%}\n {%- set ns_tool_scan.stopped = true -%}\n {%- else -%}\n {%- set follow = loop_messages[k] -%}\n {#- Resolve tool_call_id to function name -#}\n {%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}\n {%- for tc in message['tool_calls'] -%}\n {%- if tc.get('id') == follow.get('tool_call_id') -%}\n {%- set ns_tname.name = tc['function']['name'] -%}\n {%- endif -%}\n {%- endfor -%}\n {#- Handle content as string or content-parts array -#}\n {%- set tool_body = follow.get('content') -%}\n {%- if tool_body is string -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- elif tool_body is sequence and tool_body is not string -%}\n {%- set ns_txt = namespace(s='') -%}\n {%- for part in tool_body -%}\n {%- if part.get('type') == 'text' -%}\n {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}\n {%- endif -%}\n {%- endfor -%}\n {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}\n {%- else -%}\n {{- format_tool_response_block(ns_tname.name, tool_body) -}}\n {%- endif -%}\n {%- set ns_tr_out.flag = true -%}\n {%- set ns.prev_message_type = 'tool_response' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if message['content'] is string -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(message['content']) -}}\n {%- else -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {%- elif message['content'] is sequence -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'text' -%}\n {%- if role == 'model' -%}\n {{- strip_thinking(item['text']) -}}\n {%- else -%}\n {{- item['text'] | trim -}}\n {%- endif -%}\n {%- elif item['type'] == 'image' -%}\n {{- '<|image|>' -}}\n {%- set ns.prev_message_type = 'image' -%}\n {%- elif item['type'] == 'audio' -%}\n {{- '<|audio|>' -}}\n {%- set ns.prev_message_type = 'audio' -%}\n {%- elif item['type'] == 'video' -%}\n {{- '<|video|>' -}}\n {%- set ns.prev_message_type = 'video' -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}\n {{- '<|tool_response>' -}}\n {%- elif not (ns_tr_out.flag and not message.get('content')) -%}\n {{- '<turn|>\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}\n {{- '<|turn>model\\n' -}}\n {%- if not enable_thinking | default(false) -%}\n {{- '<|channel>thought\\n<channel|>' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endif -%}"
97
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29cac64c86d95f952af29aa60585c882ae47a7e3b30769b881fd6d9c2701b0a2
3
+ size 5713