Hugging Face's logo

PIXELZX
/
XION0.2-27B

Safetensors
qwen3_5
vllm
uncensored
qwen3.8
bf16
abliterated
reasoning
long-context
Model card Files
xet
 Community
pistonX commited on
Commit
39e12cb
·
verified ·
1 Parent(s): 55bfb09

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +170 -0
  3. config.json +147 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00003.safetensors +3 -0
  6. model-00002-of-00003.safetensors +3 -0
  7. model-00003-of-00003.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. preprocessor_config.json +26 -0
  10. processor_config.json +60 -0
  11. special_tokens_map.json +11 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +34 -0
  14. trainer_state.json +526 -0
.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
chat_template.jinja ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- set reasoning_instructions = '' %}
46
+ {%- if enable_thinking is undefined or enable_thinking is true %}
47
+ {%- set resolved_reasoning_effort = reasoning_effort|default('medium') %}
48
+ {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
49
+ {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
50
+ {%- endif %}
51
+ {%- if resolved_reasoning_effort == 'xhigh' %}
52
+ {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Think carefully through the task, validate key assumptions, and consider plausible alternatives. For short or routine questions, finish internal reasoning within 512 tokens. Once the answer is established, stop deliberating and give the final answer; do not repeat, restart, paraphrase the same thought, or extend reasoning without new evidence.' %}
53
+ {%- elif resolved_reasoning_effort == 'low' %}
54
+ {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused. Once the answer is established, stop deliberating and give the final answer; do not repeat, restart, or extend reasoning without new evidence.' %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if tools and tools is iterable and tools is not mapping %}
58
+ {{- '<|im_start|>system\n' }}
59
+ {%- if reasoning_instructions %}
60
+ {{- reasoning_instructions + '\n\n' }}
61
+ {%- endif %}
62
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
63
+ {%- for tool in tools %}
64
+ {{- "\n" }}
65
+ {{- tool | tojson }}
66
+ {%- endfor %}
67
+ {{- "\n</tools>" }}
68
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
69
+ {%- if messages[0].role == 'system' %}
70
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
71
+ {%- if content %}
72
+ {{- '\n\n' + content }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {{- '<|im_end|>\n' }}
76
+ {%- else %}
77
+ {%- if messages[0].role == 'system' %}
78
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
79
+ {%- if content %}
80
+ {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
81
+ {%- elif reasoning_instructions %}
82
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
83
+ {%- endif %}
84
+ {%- elif reasoning_instructions %}
85
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
86
+ {%- endif %}
87
+ {%- endif %}
88
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
89
+ {%- for message in messages[::-1] %}
90
+ {%- set index = (messages|length - 1) - loop.index0 %}
91
+ {%- if ns.multi_step_tool and message.role == "user" %}
92
+ {%- set content = render_content(message.content, false)|trim %}
93
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
94
+ {%- set ns.multi_step_tool = false %}
95
+ {%- set ns.last_query_index = index %}
96
+ {%- endif %}
97
+ {%- endif %}
98
+ {%- endfor %}
99
+ {%- if ns.multi_step_tool %}
100
+ {{- raise_exception('No user query found in messages.') }}
101
+ {%- endif %}
102
+ {%- for message in messages %}
103
+ {%- set content = render_content(message.content, true)|trim %}
104
+ {%- if message.role == "system" %}
105
+ {%- if not loop.first %}
106
+ {{- raise_exception('System message must be at the beginning.') }}
107
+ {%- endif %}
108
+ {%- elif message.role == "user" %}
109
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
110
+ {%- elif message.role == "assistant" %}
111
+ {%- set reasoning_content = '' %}
112
+ {%- if message.reasoning_content is string %}
113
+ {%- set reasoning_content = message.reasoning_content %}
114
+ {%- endif %}
115
+ {%- set reasoning_content = reasoning_content|trim %}
116
+ {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
117
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
118
+ {%- else %}
119
+ {{- '<|im_start|>' + message.role + '\n' + content }}
120
+ {%- endif %}
121
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
122
+ {%- for tool_call in message.tool_calls %}
123
+ {%- if tool_call.function is defined %}
124
+ {%- set tool_call = tool_call.function %}
125
+ {%- endif %}
126
+ {%- if loop.first %}
127
+ {%- if content|trim %}
128
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
129
+ {%- else %}
130
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
131
+ {%- endif %}
132
+ {%- else %}
133
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
134
+ {%- endif %}
135
+ {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
136
+ {%- for args_name, args_value in tool_call.arguments|items %}
137
+ {{- '<parameter=' + args_name + '>\n' }}
138
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
139
+ {{- args_value }}
140
+ {{- '\n</parameter>\n' }}
141
+ {%- endfor %}
142
+ {%- endif %}
143
+ {{- '</function>\n</tool_call>' }}
144
+ {%- endfor %}
145
+ {%- endif %}
146
+ {{- '<|im_end|>\n' }}
147
+ {%- elif message.role == "tool" %}
148
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
149
+ {{- '<|im_start|>user' }}
150
+ {%- endif %}
151
+ {{- '\n<tool_response>\n' }}
152
+ {{- content }}
153
+ {{- '\n</tool_response>' }}
154
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
155
+ {{- '<|im_end|>\n' }}
156
+ {%- elif loop.last %}
157
+ {{- '<|im_end|>\n' }}
158
+ {%- endif %}
159
+ {%- else %}
160
+ {{- raise_exception('Unexpected message role.') }}
161
+ {%- endif %}
162
+ {%- endfor %}
163
+ {%- if add_generation_prompt %}
164
+ {{- '<|im_start|>assistant\n' }}
165
+ {%- if enable_thinking is defined and enable_thinking is false %}
166
+ {{- '<think>\n\n</think>\n\n' }}
167
+ {%- else %}
168
+ {{- '<think>\n' }}
169
+ {%- endif %}
170
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "image_token_id": 248056,
9
+ "language_model_only": false,
10
+ "model_type": "qwen3_5",
11
+ "pad_token_id": 248044,
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_output_gate": true,
16
+ "bos_token_id": 248044,
17
+ "dtype": "bfloat16",
18
+ "eos_token_id": 248044,
19
+ "full_attention_interval": 4,
20
+ "head_dim": 256,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 5120,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 17408,
25
+ "layer_types": [
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "full_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "full_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "full_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "full_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "full_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "full_attention"
90
+ ],
91
+ "linear_conv_kernel_dim": 4,
92
+ "linear_key_head_dim": 128,
93
+ "linear_num_key_heads": 16,
94
+ "linear_num_value_heads": 48,
95
+ "linear_value_head_dim": 128,
96
+ "mamba_ssm_dtype": "float32",
97
+ "max_position_embeddings": 262144,
98
+ "model_type": "qwen3_5_text",
99
+ "mtp_num_hidden_layers": 1,
100
+ "mtp_use_dedicated_embeddings": false,
101
+ "num_attention_heads": 24,
102
+ "num_hidden_layers": 64,
103
+ "num_key_value_heads": 4,
104
+ "output_gate_type": "swish",
105
+ "pad_token_id": null,
106
+ "partial_rotary_factor": 0.25,
107
+ "rms_norm_eps": 1e-06,
108
+ "rope_parameters": {
109
+ "mrope_interleaved": true,
110
+ "mrope_section": [
111
+ 11,
112
+ 11,
113
+ 10
114
+ ],
115
+ "partial_rotary_factor": 0.25,
116
+ "rope_theta": 10000000,
117
+ "rope_type": "default"
118
+ },
119
+ "tie_word_embeddings": false,
120
+ "use_cache": false,
121
+ "vocab_size": 248320,
122
+ "torch_dtype": "bfloat16"
123
+ },
124
+ "tie_word_embeddings": false,
125
+ "transformers_version": "5.13.0",
126
+ "use_cache": false,
127
+ "video_token_id": 248057,
128
+ "vision_config": {
129
+ "deepstack_visual_indexes": [],
130
+ "depth": 27,
131
+ "hidden_act": "gelu_pytorch_tanh",
132
+ "hidden_size": 1152,
133
+ "in_channels": 3,
134
+ "initializer_range": 0.02,
135
+ "intermediate_size": 4304,
136
+ "model_type": "qwen3_5_vision",
137
+ "num_heads": 16,
138
+ "num_position_embeddings": 2304,
139
+ "out_hidden_size": 5120,
140
+ "patch_size": 16,
141
+ "spatial_merge_size": 2,
142
+ "temporal_patch_size": 2
143
+ },
144
+ "vision_end_token_id": 248054,
145
+ "vision_start_token_id": 248053,
146
+ "torch_dtype": "bfloat16"
147
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.13.0"
13
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887c557c92915aac4383365a395cbdbc28ae698e6a7ce5f6786fd36867e3c275
3
+ size 49979080424
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59960d23f11549a5152101edcbe39c471718605aea63a13d90c19e0f95936e83
3
+ size 49671140304
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aaed2202f1fb600a665f001bd1044c2fef377860032ea46257eb863f7817870
3
+ size 8855383560
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "merge_size": 2,
18
+ "patch_size": 16,
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "longest_edge": 16777216,
23
+ "shortest_edge": 65536
24
+ },
25
+ "temporal_patch_size": 2
26
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_bos_token": "<|audio_start|>",
3
+ "audio_eos_token": "<|audio_end|>",
4
+ "audio_token": "<|audio_pad|>",
5
+ "eos_token": "<|im_end|>",
6
+ "image_token": "<|image_pad|>",
7
+ "pad_token": "<|endoftext|>",
8
+ "video_token": "<|video_pad|>",
9
+ "vision_bos_token": "<|vision_start|>",
10
+ "vision_eos_token": "<|vision_end|>"
11
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": true,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "padding_side": "right",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,526 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 22,
7
+ "global_step": 66,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.045454545454545456,
14
+ "grad_norm": 13.541594505310059,
15
+ "learning_rate": 1e-05,
16
+ "loss": 1.687255859375,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.09090909090909091,
21
+ "grad_norm": 270.9620056152344,
22
+ "learning_rate": 9.994336695915041e-06,
23
+ "loss": 4.320972442626953,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.13636363636363635,
28
+ "grad_norm": 8.045546531677246,
29
+ "learning_rate": 9.977359612865424e-06,
30
+ "loss": 0.990966796875,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.18181818181818182,
35
+ "grad_norm": 4.051703453063965,
36
+ "learning_rate": 9.949107209404664e-06,
37
+ "loss": 1.09613037109375,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.22727272727272727,
42
+ "grad_norm": 2.503697633743286,
43
+ "learning_rate": 9.909643486313533e-06,
44
+ "loss": 1.016815185546875,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.2727272727272727,
49
+ "grad_norm": 3.1819581985473633,
50
+ "learning_rate": 9.859057841617709e-06,
51
+ "loss": 0.91766357421875,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.3181818181818182,
56
+ "grad_norm": 1.810927391052246,
57
+ "learning_rate": 9.797464868072489e-06,
58
+ "loss": 0.9587249755859375,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.36363636363636365,
63
+ "grad_norm": 1.6619356870651245,
64
+ "learning_rate": 9.725004093573343e-06,
65
+ "loss": 0.80902099609375,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.4090909090909091,
70
+ "grad_norm": 2.2837491035461426,
71
+ "learning_rate": 9.641839665080363e-06,
72
+ "loss": 0.8079757690429688,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.45454545454545453,
77
+ "grad_norm": 3.019440174102783,
78
+ "learning_rate": 9.548159976772593e-06,
79
+ "loss": 0.8288116455078125,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.5,
84
+ "grad_norm": 1.1921716928482056,
85
+ "learning_rate": 9.444177243274619e-06,
86
+ "loss": 0.6759376525878906,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.5454545454545454,
91
+ "grad_norm": 2.224130153656006,
92
+ "learning_rate": 9.330127018922195e-06,
93
+ "loss": 0.54034423828125,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.5909090909090909,
98
+ "grad_norm": 1.386547327041626,
99
+ "learning_rate": 9.206267664155906e-06,
100
+ "loss": 0.49675750732421875,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.6363636363636364,
105
+ "grad_norm": 1.4452524185180664,
106
+ "learning_rate": 9.07287976025168e-06,
107
+ "loss": 0.4326019287109375,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.6818181818181818,
112
+ "grad_norm": 2.8639578819274902,
113
+ "learning_rate": 8.930265473713939e-06,
114
+ "loss": 0.587005615234375,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.7272727272727273,
119
+ "grad_norm": 1.1509618759155273,
120
+ "learning_rate": 8.778747871771293e-06,
121
+ "loss": 0.49512481689453125,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.7727272727272727,
126
+ "grad_norm": 1.06486177444458,
127
+ "learning_rate": 8.61867019052535e-06,
128
+ "loss": 0.6640739440917969,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.8181818181818182,
133
+ "grad_norm": 0.9991989731788635,
134
+ "learning_rate": 8.450395057410561e-06,
135
+ "loss": 0.437957763671875,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.8636363636363636,
140
+ "grad_norm": 0.7819029092788696,
141
+ "learning_rate": 8.274303669726427e-06,
142
+ "loss": 0.5671710968017578,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.9090909090909091,
147
+ "grad_norm": 0.8972281813621521,
148
+ "learning_rate": 8.090794931103026e-06,
149
+ "loss": 0.3094291687011719,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.9545454545454546,
154
+ "grad_norm": 0.8230551481246948,
155
+ "learning_rate": 7.900284547855992e-06,
156
+ "loss": 0.42014312744140625,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 1.0,
161
+ "grad_norm": 0.9112458229064941,
162
+ "learning_rate": 7.703204087277989e-06,
163
+ "loss": 0.3252525329589844,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 1.0,
168
+ "eval_loss": 0.59442138671875,
169
+ "eval_runtime": 13.685,
170
+ "eval_samples_per_second": 0.365,
171
+ "eval_steps_per_second": 0.073,
172
+ "step": 22
173
+ },
174
+ {
175
+ "checkpoint_runtime": 130.4115
176
+ },
177
+ {
178
+ "epoch": 1.0454545454545454,
179
+ "grad_norm": 1.6123707294464111,
180
+ "learning_rate": 7.500000000000001e-06,
181
+ "loss": 0.5166397094726562,
182
+ "step": 23
183
+ },
184
+ {
185
+ "epoch": 1.0909090909090908,
186
+ "grad_norm": 1.3553637266159058,
187
+ "learning_rate": 7.291132608637053e-06,
188
+ "loss": 0.3297233581542969,
189
+ "step": 24
190
+ },
191
+ {
192
+ "epoch": 1.1363636363636362,
193
+ "grad_norm": 1.3093994855880737,
194
+ "learning_rate": 7.0770750650094335e-06,
195
+ "loss": 0.49069786071777344,
196
+ "step": 25
197
+ },
198
+ {
199
+ "epoch": 1.1818181818181819,
200
+ "grad_norm": 0.996208667755127,
201
+ "learning_rate": 6.858312278301638e-06,
202
+ "loss": 0.2602996826171875,
203
+ "step": 26
204
+ },
205
+ {
206
+ "epoch": 1.2272727272727273,
207
+ "grad_norm": 0.8691992163658142,
208
+ "learning_rate": 6.635339816587109e-06,
209
+ "loss": 0.09621810913085938,
210
+ "step": 27
211
+ },
212
+ {
213
+ "epoch": 1.2727272727272727,
214
+ "grad_norm": 0.73832106590271,
215
+ "learning_rate": 6.408662784207149e-06,
216
+ "loss": 0.2693767547607422,
217
+ "step": 28
218
+ },
219
+ {
220
+ "epoch": 1.3181818181818181,
221
+ "grad_norm": 0.9352995753288269,
222
+ "learning_rate": 6.178794677547138e-06,
223
+ "loss": 0.2981605529785156,
224
+ "step": 29
225
+ },
226
+ {
227
+ "epoch": 1.3636363636363638,
228
+ "grad_norm": 0.6079849004745483,
229
+ "learning_rate": 5.946256221802052e-06,
230
+ "loss": 0.26114463806152344,
231
+ "step": 30
232
+ },
233
+ {
234
+ "epoch": 1.4090909090909092,
235
+ "grad_norm": 1.1613916158676147,
236
+ "learning_rate": 5.711574191366427e-06,
237
+ "loss": 0.3663311004638672,
238
+ "step": 31
239
+ },
240
+ {
241
+ "epoch": 1.4545454545454546,
242
+ "grad_norm": 1.0265836715698242,
243
+ "learning_rate": 5.475280216520913e-06,
244
+ "loss": 0.13217544555664062,
245
+ "step": 32
246
+ },
247
+ {
248
+ "epoch": 1.5,
249
+ "grad_norm": 0.9267441630363464,
250
+ "learning_rate": 5.237909579118713e-06,
251
+ "loss": 0.3060760498046875,
252
+ "step": 33
253
+ },
254
+ {
255
+ "epoch": 1.5454545454545454,
256
+ "grad_norm": 0.6758596301078796,
257
+ "learning_rate": 5e-06,
258
+ "loss": 0.053920745849609375,
259
+ "step": 34
260
+ },
261
+ {
262
+ "epoch": 1.5909090909090908,
263
+ "grad_norm": 0.6371091604232788,
264
+ "learning_rate": 4.762090420881289e-06,
265
+ "loss": 0.11317062377929688,
266
+ "step": 35
267
+ },
268
+ {
269
+ "epoch": 1.6363636363636362,
270
+ "grad_norm": 0.6892620325088501,
271
+ "learning_rate": 4.524719783479088e-06,
272
+ "loss": 0.1634387969970703,
273
+ "step": 36
274
+ },
275
+ {
276
+ "epoch": 1.6818181818181817,
277
+ "grad_norm": 1.267598032951355,
278
+ "learning_rate": 4.2884258086335755e-06,
279
+ "loss": 0.1157989501953125,
280
+ "step": 37
281
+ },
282
+ {
283
+ "epoch": 1.7272727272727273,
284
+ "grad_norm": 0.618965208530426,
285
+ "learning_rate": 4.053743778197951e-06,
286
+ "loss": 0.2590446472167969,
287
+ "step": 38
288
+ },
289
+ {
290
+ "epoch": 1.7727272727272727,
291
+ "grad_norm": 0.8626583814620972,
292
+ "learning_rate": 3.821205322452863e-06,
293
+ "loss": 0.4122934341430664,
294
+ "step": 39
295
+ },
296
+ {
297
+ "epoch": 1.8181818181818183,
298
+ "grad_norm": 0.5675498843193054,
299
+ "learning_rate": 3.5913372157928515e-06,
300
+ "loss": 0.18222999572753906,
301
+ "step": 40
302
+ },
303
+ {
304
+ "epoch": 1.8636363636363638,
305
+ "grad_norm": 1.346577525138855,
306
+ "learning_rate": 3.3646601834128924e-06,
307
+ "loss": 0.36645030975341797,
308
+ "step": 41
309
+ },
310
+ {
311
+ "epoch": 1.9090909090909092,
312
+ "grad_norm": 0.5783951282501221,
313
+ "learning_rate": 3.141687721698363e-06,
314
+ "loss": 0.19093704223632812,
315
+ "step": 42
316
+ },
317
+ {
318
+ "epoch": 1.9545454545454546,
319
+ "grad_norm": 0.7677918672561646,
320
+ "learning_rate": 2.9229249349905686e-06,
321
+ "loss": 0.24652671813964844,
322
+ "step": 43
323
+ },
324
+ {
325
+ "epoch": 2.0,
326
+ "grad_norm": 0.6522639393806458,
327
+ "learning_rate": 2.708867391362948e-06,
328
+ "loss": 0.13533401489257812,
329
+ "step": 44
330
+ },
331
+ {
332
+ "epoch": 2.0,
333
+ "eval_loss": 0.59344482421875,
334
+ "eval_runtime": 4.3126,
335
+ "eval_samples_per_second": 1.159,
336
+ "eval_steps_per_second": 0.232,
337
+ "step": 44
338
+ },
339
+ {
340
+ "checkpoint_runtime": 134.2782
341
+ },
342
+ {
343
+ "epoch": 2.0454545454545454,
344
+ "grad_norm": 1.315116286277771,
345
+ "learning_rate": 2.5000000000000015e-06,
346
+ "loss": 0.2724342346191406,
347
+ "step": 45
348
+ },
349
+ {
350
+ "epoch": 2.090909090909091,
351
+ "grad_norm": 0.5187699198722839,
352
+ "learning_rate": 2.296795912722014e-06,
353
+ "loss": 0.18209326267242432,
354
+ "step": 46
355
+ },
356
+ {
357
+ "epoch": 2.1363636363636362,
358
+ "grad_norm": 0.9916004538536072,
359
+ "learning_rate": 2.09971545214401e-06,
360
+ "loss": 0.2614755630493164,
361
+ "step": 47
362
+ },
363
+ {
364
+ "epoch": 2.1818181818181817,
365
+ "grad_norm": 0.5112076997756958,
366
+ "learning_rate": 1.9092050688969736e-06,
367
+ "loss": 0.1507863998413086,
368
+ "step": 48
369
+ },
370
+ {
371
+ "epoch": 2.227272727272727,
372
+ "grad_norm": 0.3336804211139679,
373
+ "learning_rate": 1.7256963302735752e-06,
374
+ "loss": 0.024288177490234375,
375
+ "step": 49
376
+ },
377
+ {
378
+ "epoch": 2.2727272727272725,
379
+ "grad_norm": 0.40631377696990967,
380
+ "learning_rate": 1.549604942589441e-06,
381
+ "loss": 0.19109153747558594,
382
+ "step": 50
383
+ },
384
+ {
385
+ "epoch": 2.3181818181818183,
386
+ "grad_norm": 0.8899633288383484,
387
+ "learning_rate": 1.3813298094746491e-06,
388
+ "loss": 0.17161941528320312,
389
+ "step": 51
390
+ },
391
+ {
392
+ "epoch": 2.3636363636363638,
393
+ "grad_norm": 0.5578643679618835,
394
+ "learning_rate": 1.2212521282287093e-06,
395
+ "loss": 0.17924213409423828,
396
+ "step": 52
397
+ },
398
+ {
399
+ "epoch": 2.409090909090909,
400
+ "grad_norm": 1.057443618774414,
401
+ "learning_rate": 1.0697345262860638e-06,
402
+ "loss": 0.21059799194335938,
403
+ "step": 53
404
+ },
405
+ {
406
+ "epoch": 2.4545454545454546,
407
+ "grad_norm": 0.6124624609947205,
408
+ "learning_rate": 9.271202397483214e-07,
409
+ "loss": 0.050838470458984375,
410
+ "step": 54
411
+ },
412
+ {
413
+ "epoch": 2.5,
414
+ "grad_norm": 0.5138548016548157,
415
+ "learning_rate": 7.937323358440935e-07,
416
+ "loss": 0.22317028045654297,
417
+ "step": 55
418
+ },
419
+ {
420
+ "epoch": 2.5454545454545454,
421
+ "grad_norm": 0.5870931148529053,
422
+ "learning_rate": 6.698729810778065e-07,
423
+ "loss": 0.02097320556640625,
424
+ "step": 56
425
+ },
426
+ {
427
+ "epoch": 2.590909090909091,
428
+ "grad_norm": 0.47857600450515747,
429
+ "learning_rate": 5.558227567253832e-07,
430
+ "loss": 0.056339263916015625,
431
+ "step": 57
432
+ },
433
+ {
434
+ "epoch": 2.6363636363636362,
435
+ "grad_norm": 0.4128285050392151,
436
+ "learning_rate": 4.5184002322740784e-07,
437
+ "loss": 0.10932445526123047,
438
+ "step": 58
439
+ },
440
+ {
441
+ "epoch": 2.6818181818181817,
442
+ "grad_norm": 0.9088109135627747,
443
+ "learning_rate": 3.581603349196372e-07,
444
+ "loss": 0.04517364501953125,
445
+ "step": 59
446
+ },
447
+ {
448
+ "epoch": 2.7272727272727275,
449
+ "grad_norm": 0.5057564973831177,
450
+ "learning_rate": 2.7499590642665773e-07,
451
+ "loss": 0.19766902923583984,
452
+ "step": 60
453
+ },
454
+ {
455
+ "epoch": 2.7727272727272725,
456
+ "grad_norm": 0.792408287525177,
457
+ "learning_rate": 2.0253513192751374e-07,
458
+ "loss": 0.33954524993896484,
459
+ "step": 61
460
+ },
461
+ {
462
+ "epoch": 2.8181818181818183,
463
+ "grad_norm": 0.47474050521850586,
464
+ "learning_rate": 1.4094215838229176e-07,
465
+ "loss": 0.12943077087402344,
466
+ "step": 62
467
+ },
468
+ {
469
+ "epoch": 2.8636363636363638,
470
+ "grad_norm": 0.9088992476463318,
471
+ "learning_rate": 9.035651368646647e-08,
472
+ "loss": 0.3276538848876953,
473
+ "step": 63
474
+ },
475
+ {
476
+ "epoch": 2.909090909090909,
477
+ "grad_norm": 0.4451668858528137,
478
+ "learning_rate": 5.089279059533658e-08,
479
+ "loss": 0.1589193344116211,
480
+ "step": 64
481
+ },
482
+ {
483
+ "epoch": 2.9545454545454546,
484
+ "grad_norm": 0.6257097721099854,
485
+ "learning_rate": 2.264038713457706e-08,
486
+ "loss": 0.2027444839477539,
487
+ "step": 65
488
+ },
489
+ {
490
+ "epoch": 3.0,
491
+ "grad_norm": 0.4987045228481293,
492
+ "learning_rate": 5.6633040849601865e-09,
493
+ "loss": 0.09051704406738281,
494
+ "step": 66
495
+ },
496
+ {
497
+ "epoch": 3.0,
498
+ "eval_loss": 0.61431884765625,
499
+ "eval_runtime": 4.3337,
500
+ "eval_samples_per_second": 1.154,
501
+ "eval_steps_per_second": 0.231,
502
+ "step": 66
503
+ }
504
+ ],
505
+ "logging_steps": 1.0,
506
+ "max_steps": 66,
507
+ "num_input_tokens_seen": 0,
508
+ "num_train_epochs": 3,
509
+ "save_steps": 22,
510
+ "stateful_callbacks": {
511
+ "TrainerControl": {
512
+ "args": {
513
+ "should_epoch_stop": false,
514
+ "should_evaluate": false,
515
+ "should_log": false,
516
+ "should_save": true,
517
+ "should_training_stop": true
518
+ },
519
+ "attributes": {}
520
+ }
521
+ },
522
+ "total_flos": 8.409622391826678e+17,
523
+ "train_batch_size": 1,
524
+ "trial_name": null,
525
+ "trial_params": null
526
+ }