ApacheOne commited on
Commit
12f1f13
·
verified ·
1 Parent(s): ae1053c

Upload modelopt-v4

Browse files
modelopt-v4/_nvfp4_qcfg_debug.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quant_cfg": {
3
+ "*weight_quantizer": {
4
+ "num_bits": [
5
+ 2,
6
+ 1
7
+ ],
8
+ "block_sizes": {
9
+ "-1": 16,
10
+ "type": "dynamic",
11
+ "scale_bits": [
12
+ 4,
13
+ 3
14
+ ]
15
+ },
16
+ "enable": true
17
+ },
18
+ "*input_quantizer": {
19
+ "enable": false
20
+ },
21
+ "nn.BatchNorm1d": {
22
+ "*": {
23
+ "enable": false
24
+ }
25
+ },
26
+ "nn.BatchNorm2d": {
27
+ "*": {
28
+ "enable": false
29
+ }
30
+ },
31
+ "nn.BatchNorm3d": {
32
+ "*": {
33
+ "enable": false
34
+ }
35
+ },
36
+ "nn.LeakyReLU": {
37
+ "*": {
38
+ "enable": false
39
+ }
40
+ },
41
+ "*lm_head*": {
42
+ "enable": false
43
+ },
44
+ "*proj_out.*": {
45
+ "enable": false
46
+ },
47
+ "*block_sparse_moe.gate*": {
48
+ "enable": false
49
+ },
50
+ "*router*": {
51
+ "enable": false
52
+ },
53
+ "*mlp.gate.*": {
54
+ "enable": false
55
+ },
56
+ "*mlp.shared_expert_gate.*": {
57
+ "enable": false
58
+ },
59
+ "*linear_attn.conv1d*": {
60
+ "enable": false
61
+ },
62
+ "*mixer.conv1d*": {
63
+ "enable": false
64
+ },
65
+ "*output_layer*": {
66
+ "enable": false
67
+ },
68
+ "output.*": {
69
+ "enable": false
70
+ },
71
+ "default": {
72
+ "enable": false
73
+ },
74
+ "*norm*": {
75
+ "enable": false
76
+ },
77
+ "*layernorm*": {
78
+ "enable": false
79
+ },
80
+ "*LayerNorm*": {
81
+ "enable": false
82
+ },
83
+ "*rotary*": {
84
+ "enable": false
85
+ },
86
+ "*bias*": {
87
+ "enable": false
88
+ },
89
+ "lm_head*": {
90
+ "enable": false
91
+ },
92
+ "lm_head.weight_quantizer": {
93
+ "enable": false
94
+ },
95
+ "*visual.blocks.*.mlp.linear_fc1*": {
96
+ "enable": false
97
+ },
98
+ "*visual.blocks.*.mlp.linear_fc2*": {
99
+ "enable": false
100
+ },
101
+ "model.visual.blocks.*.mlp.linear_fc1*": {
102
+ "enable": false
103
+ },
104
+ "model.visual.blocks.*.mlp.linear_fc2*": {
105
+ "enable": false
106
+ }
107
+ },
108
+ "algorithm": null
109
+ }
modelopt-v4/_quant_summary/.quant_summary.txt ADDED
The diff for this file is too large to render. See raw diff
 
modelopt-v4/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
3
+ }
modelopt-v4/config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen3_vl",
8
+ "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 151643,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 151645,
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 12288,
19
+ "max_position_embeddings": 262144,
20
+ "model_type": "qwen3_vl_text",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 36,
23
+ "num_key_value_heads": 8,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_scaling": {
26
+ "mrope_interleaved": true,
27
+ "mrope_section": [
28
+ 24,
29
+ 20,
30
+ 20
31
+ ],
32
+ "rope_type": "default"
33
+ },
34
+ "rope_theta": 5000000,
35
+ "use_cache": true,
36
+ "vocab_size": 151936
37
+ },
38
+ "tie_word_embeddings": false,
39
+ "transformers_version": "4.57.6",
40
+ "video_token_id": 151656,
41
+ "vision_config": {
42
+ "deepstack_visual_indexes": [
43
+ 8,
44
+ 16,
45
+ 24
46
+ ],
47
+ "depth": 27,
48
+ "dtype": "bfloat16",
49
+ "hidden_act": "gelu_pytorch_tanh",
50
+ "hidden_size": 1152,
51
+ "in_channels": 3,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4304,
54
+ "model_type": "qwen3_vl",
55
+ "num_heads": 16,
56
+ "num_position_embeddings": 2304,
57
+ "out_hidden_size": 4096,
58
+ "patch_size": 16,
59
+ "spatial_merge_size": 2,
60
+ "temporal_patch_size": 2
61
+ },
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "quantization_config": {
65
+ "config_groups": {
66
+ "group_0": {
67
+ "input_activations": {
68
+ "dynamic": false,
69
+ "num_bits": 4,
70
+ "type": "float",
71
+ "group_size": 16
72
+ },
73
+ "weights": {
74
+ "dynamic": false,
75
+ "num_bits": 4,
76
+ "type": "float",
77
+ "group_size": 16
78
+ },
79
+ "targets": [
80
+ "Linear"
81
+ ]
82
+ }
83
+ },
84
+ "ignore": [
85
+ "lm_head",
86
+ "model.visual.blocks.0.mlp*",
87
+ "model.visual.blocks.1.mlp*",
88
+ "model.visual.blocks.10.mlp*",
89
+ "model.visual.blocks.11.mlp*",
90
+ "model.visual.blocks.12.mlp*",
91
+ "model.visual.blocks.13.mlp*",
92
+ "model.visual.blocks.14.mlp*",
93
+ "model.visual.blocks.15.mlp*",
94
+ "model.visual.blocks.16.mlp*",
95
+ "model.visual.blocks.17.mlp*",
96
+ "model.visual.blocks.18.mlp*",
97
+ "model.visual.blocks.19.mlp*",
98
+ "model.visual.blocks.2.mlp*",
99
+ "model.visual.blocks.20.mlp*",
100
+ "model.visual.blocks.21.mlp*",
101
+ "model.visual.blocks.22.mlp*",
102
+ "model.visual.blocks.23.mlp*",
103
+ "model.visual.blocks.24.mlp*",
104
+ "model.visual.blocks.25.mlp*",
105
+ "model.visual.blocks.26.mlp*",
106
+ "model.visual.blocks.3.mlp*",
107
+ "model.visual.blocks.4.mlp*",
108
+ "model.visual.blocks.5.mlp*",
109
+ "model.visual.blocks.6.mlp*",
110
+ "model.visual.blocks.7.mlp*",
111
+ "model.visual.blocks.8.mlp*",
112
+ "model.visual.blocks.9.mlp*"
113
+ ],
114
+ "quant_algo": "NVFP4",
115
+ "producer": {
116
+ "name": "modelopt",
117
+ "version": "0.43.0"
118
+ },
119
+ "quant_method": "modelopt"
120
+ }
121
+ }
modelopt-v4/configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"framework": "pytorch", "task": "text-generation", "allow_remote": true}
modelopt-v4/conversion_note.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "source_model_dir": "/content/ApacheOne-expimodel/merged-load-v3",
3
+ "source_key_count": 759,
4
+ "loaded_key_count": 759,
5
+ "missing_key_count": 0,
6
+ "extra_key_count": 0,
7
+ "modelopt_version": "0.43.0",
8
+ "torch_version": "2.10.0+cu128",
9
+ "torch_dtype_load": "bfloat16",
10
+ "weight_only_nvfp4": true,
11
+ "quantize_lm_head": false,
12
+ "skip_visual_mlp_linears": true,
13
+ "disabled_quantizer_count": 165,
14
+ "failed_disable_quantizer_count": 0,
15
+ "patched_amax_count": 320,
16
+ "skipped_amax_count": 0,
17
+ "single_safetensors_out": "/content/HiDream-O1-Image-Dev-full-NVFP4-modelopt-v4.safetensors"
18
+ }
modelopt-v4/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.6"
13
+ }
modelopt-v4/hf_quant_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.43.0"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": null,
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "model.visual.blocks.0.mlp*",
13
+ "model.visual.blocks.1.mlp*",
14
+ "model.visual.blocks.10.mlp*",
15
+ "model.visual.blocks.11.mlp*",
16
+ "model.visual.blocks.12.mlp*",
17
+ "model.visual.blocks.13.mlp*",
18
+ "model.visual.blocks.14.mlp*",
19
+ "model.visual.blocks.15.mlp*",
20
+ "model.visual.blocks.16.mlp*",
21
+ "model.visual.blocks.17.mlp*",
22
+ "model.visual.blocks.18.mlp*",
23
+ "model.visual.blocks.19.mlp*",
24
+ "model.visual.blocks.2.mlp*",
25
+ "model.visual.blocks.20.mlp*",
26
+ "model.visual.blocks.21.mlp*",
27
+ "model.visual.blocks.22.mlp*",
28
+ "model.visual.blocks.23.mlp*",
29
+ "model.visual.blocks.24.mlp*",
30
+ "model.visual.blocks.25.mlp*",
31
+ "model.visual.blocks.26.mlp*",
32
+ "model.visual.blocks.3.mlp*",
33
+ "model.visual.blocks.4.mlp*",
34
+ "model.visual.blocks.5.mlp*",
35
+ "model.visual.blocks.6.mlp*",
36
+ "model.visual.blocks.7.mlp*",
37
+ "model.visual.blocks.8.mlp*",
38
+ "model.visual.blocks.9.mlp*"
39
+ ]
40
+ }
41
+ }
modelopt-v4/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
modelopt-v4/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fb78badd2066a545927486bbff6dbe2700967d9a80193fd177f01d78651373
3
+ size 4997523732
modelopt-v4/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744144d3832d5d12740241b618cb4138e3b735a1d33624787ed3f303c083220f
3
+ size 1906627568
modelopt-v4/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
modelopt-v4/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
modelopt-v4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
modelopt-v4/tokenizer_config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>",
228
+ "<|boi_token|>",
229
+ "<|bor_token|>",
230
+ "<|eor_token|>",
231
+ "<|bot_token|>",
232
+ "<|tms_token|>"
233
+ ],
234
+ "bos_token": null,
235
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
236
+ "clean_up_tokenization_spaces": false,
237
+ "eos_token": "<|im_end|>",
238
+ "errors": "replace",
239
+ "model_max_length": 262144,
240
+ "pad_token": "<|endoftext|>",
241
+ "split_special_tokens": false,
242
+ "tokenizer_class": "Qwen2Tokenizer",
243
+ "unk_token": null
244
+ }
modelopt-v4/video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
modelopt-v4/vocab.json ADDED
The diff for this file is too large to render. See raw diff