keep latest 2 step ckpts for cv40-60-patch2 (yijiangli's retention ruling 2026-09-14)
Browse files- cv40-60-patch2/step13/chat_template.jinja +0 -122
- cv40-60-patch2/step13/config.json +0 -112
- cv40-60-patch2/step13/generation_config.json +0 -9
- cv40-60-patch2/step13/model.safetensors +0 -3
- cv40-60-patch2/step13/processor_config.json +0 -60
- cv40-60-patch2/step13/tokenizer.json +0 -3
- cv40-60-patch2/step13/tokenizer_config.json +0 -32
- cv40-60-patch2/step26/chat_template.jinja +0 -122
- cv40-60-patch2/step26/config.json +0 -112
- cv40-60-patch2/step26/generation_config.json +0 -9
- cv40-60-patch2/step26/model.safetensors +0 -3
- cv40-60-patch2/step26/processor_config.json +0 -60
- cv40-60-patch2/step26/tokenizer.json +0 -3
- cv40-60-patch2/step26/tokenizer_config.json +0 -32
cv40-60-patch2/step13/chat_template.jinja
DELETED
|
@@ -1,122 +0,0 @@
|
|
| 1 |
-
{%- set _enable_thinking = enable_thinking if enable_thinking is defined else none %}
|
| 2 |
-
{%- if tools %}
|
| 3 |
-
{{- '<|im_start|>system\n' }}
|
| 4 |
-
{%- if messages[0].role == 'system' %}
|
| 5 |
-
{%- if messages[0].content is string %}
|
| 6 |
-
{{- messages[0].content }}
|
| 7 |
-
{%- else %}
|
| 8 |
-
{%- for content in messages[0].content %}
|
| 9 |
-
{%- if 'text' in content %}
|
| 10 |
-
{{- content.text }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- endfor %}
|
| 13 |
-
{%- endif %}
|
| 14 |
-
{{- '\n\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{{- "# 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>" }}
|
| 17 |
-
{%- for tool in tools %}
|
| 18 |
-
{{- "\n" }}
|
| 19 |
-
{{- tool | tojson }}
|
| 20 |
-
{%- endfor %}
|
| 21 |
-
{{- "\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" }}
|
| 22 |
-
{%- else %}
|
| 23 |
-
{%- if messages[0].role == 'system' %}
|
| 24 |
-
{{- '<|im_start|>system\n' }}
|
| 25 |
-
{%- if messages[0].content is string %}
|
| 26 |
-
{{- messages[0].content }}
|
| 27 |
-
{%- else %}
|
| 28 |
-
{%- for content in messages[0].content %}
|
| 29 |
-
{%- if 'text' in content %}
|
| 30 |
-
{{- content.text }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- endfor %}
|
| 33 |
-
{%- endif %}
|
| 34 |
-
{{- '<|im_end|>\n' }}
|
| 35 |
-
{%- endif %}
|
| 36 |
-
{%- endif %}
|
| 37 |
-
{%- set image_count = namespace(value=0) %}
|
| 38 |
-
{%- set video_count = namespace(value=0) %}
|
| 39 |
-
{%- for message in messages %}
|
| 40 |
-
{%- if message.role == "user" %}
|
| 41 |
-
{{- '<|im_start|>' + message.role + '\n' }}
|
| 42 |
-
{%- if message.content is string %}
|
| 43 |
-
{{- message.content }}
|
| 44 |
-
{%- else %}
|
| 45 |
-
{%- for content in message.content %}
|
| 46 |
-
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 47 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 48 |
-
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 49 |
-
<|vision_start|><|image_pad|><|vision_end|>
|
| 50 |
-
{%- elif content.type == 'video' or 'video' in content %}
|
| 51 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 52 |
-
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 53 |
-
<|vision_start|><|video_pad|><|vision_end|>
|
| 54 |
-
{%- elif 'text' in content %}
|
| 55 |
-
{{- content.text }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endfor %}
|
| 58 |
-
{%- endif %}
|
| 59 |
-
{{- '<|im_end|>\n' }}
|
| 60 |
-
{%- elif message.role == "assistant" %}
|
| 61 |
-
{{- '<|im_start|>' + message.role + '\n' }}
|
| 62 |
-
{%- if message.content is string %}
|
| 63 |
-
{{- message.content }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- for content_item in message.content %}
|
| 66 |
-
{%- if 'text' in content_item %}
|
| 67 |
-
{{- content_item.text }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
-
{%- if message.tool_calls %}
|
| 72 |
-
{%- for tool_call in message.tool_calls %}
|
| 73 |
-
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 74 |
-
{{- '\n' }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- if tool_call.function %}
|
| 77 |
-
{%- set tool_call = tool_call.function %}
|
| 78 |
-
{%- endif %}
|
| 79 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 80 |
-
{{- tool_call.name }}
|
| 81 |
-
{{- '", "arguments": ' }}
|
| 82 |
-
{%- if tool_call.arguments is string %}
|
| 83 |
-
{{- tool_call.arguments }}
|
| 84 |
-
{%- else %}
|
| 85 |
-
{{- tool_call.arguments | tojson }}
|
| 86 |
-
{%- endif %}
|
| 87 |
-
{{- '}\n</tool_call>' }}
|
| 88 |
-
{%- endfor %}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{{- '<|im_end|>\n' }}
|
| 91 |
-
{%- elif message.role == "tool" %}
|
| 92 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 93 |
-
{{- '<|im_start|>user' }}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{{- '\n<tool_response>\n' }}
|
| 96 |
-
{%- if message.content is string %}
|
| 97 |
-
{{- message.content }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{%- for content in message.content %}
|
| 100 |
-
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 101 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 102 |
-
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 103 |
-
<|vision_start|><|image_pad|><|vision_end|>
|
| 104 |
-
{%- elif content.type == 'video' or 'video' in content %}
|
| 105 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 106 |
-
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 107 |
-
<|vision_start|><|video_pad|><|vision_end|>
|
| 108 |
-
{%- elif 'text' in content %}
|
| 109 |
-
{{- content.text }}
|
| 110 |
-
{%- endif %}
|
| 111 |
-
{%- endfor %}
|
| 112 |
-
{%- endif %}
|
| 113 |
-
{{- '\n</tool_response>' }}
|
| 114 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- endif %}
|
| 117 |
-
{%- endif %}
|
| 118 |
-
{%- endfor %}
|
| 119 |
-
{%- if add_generation_prompt %}
|
| 120 |
-
{{- '<|im_start|>assistant\n' }}
|
| 121 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 122 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step13/config.json
DELETED
|
@@ -1,112 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "float32",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 2560,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 9216,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"linear_attention",
|
| 50 |
-
"linear_attention",
|
| 51 |
-
"linear_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"linear_attention",
|
| 54 |
-
"linear_attention",
|
| 55 |
-
"linear_attention",
|
| 56 |
-
"full_attention"
|
| 57 |
-
],
|
| 58 |
-
"linear_conv_kernel_dim": 4,
|
| 59 |
-
"linear_key_head_dim": 128,
|
| 60 |
-
"linear_num_key_heads": 16,
|
| 61 |
-
"linear_num_value_heads": 32,
|
| 62 |
-
"linear_value_head_dim": 128,
|
| 63 |
-
"mamba_ssm_dtype": "float32",
|
| 64 |
-
"max_position_embeddings": 262144,
|
| 65 |
-
"mlp_only_layers": [],
|
| 66 |
-
"model_type": "qwen3_5_text",
|
| 67 |
-
"mtp_num_hidden_layers": 1,
|
| 68 |
-
"mtp_use_dedicated_embeddings": false,
|
| 69 |
-
"num_attention_heads": 16,
|
| 70 |
-
"num_hidden_layers": 32,
|
| 71 |
-
"num_key_value_heads": 4,
|
| 72 |
-
"pad_token_id": null,
|
| 73 |
-
"partial_rotary_factor": 0.25,
|
| 74 |
-
"rms_norm_eps": 1e-06,
|
| 75 |
-
"rope_parameters": {
|
| 76 |
-
"mrope_interleaved": true,
|
| 77 |
-
"mrope_section": [
|
| 78 |
-
11,
|
| 79 |
-
11,
|
| 80 |
-
10
|
| 81 |
-
],
|
| 82 |
-
"partial_rotary_factor": 0.25,
|
| 83 |
-
"rope_theta": 10000000,
|
| 84 |
-
"rope_type": "default"
|
| 85 |
-
},
|
| 86 |
-
"tie_word_embeddings": true,
|
| 87 |
-
"use_cache": true,
|
| 88 |
-
"vocab_size": 248320
|
| 89 |
-
},
|
| 90 |
-
"tie_word_embeddings": true,
|
| 91 |
-
"transformers_version": "5.5.0",
|
| 92 |
-
"video_token_id": 248057,
|
| 93 |
-
"vision_config": {
|
| 94 |
-
"deepstack_visual_indexes": [],
|
| 95 |
-
"depth": 24,
|
| 96 |
-
"dtype": "bfloat16",
|
| 97 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 98 |
-
"hidden_size": 1024,
|
| 99 |
-
"in_channels": 3,
|
| 100 |
-
"initializer_range": 0.02,
|
| 101 |
-
"intermediate_size": 4096,
|
| 102 |
-
"model_type": "qwen3_5",
|
| 103 |
-
"num_heads": 16,
|
| 104 |
-
"num_position_embeddings": 2304,
|
| 105 |
-
"out_hidden_size": 2560,
|
| 106 |
-
"patch_size": 16,
|
| 107 |
-
"spatial_merge_size": 2,
|
| 108 |
-
"temporal_patch_size": 2
|
| 109 |
-
},
|
| 110 |
-
"vision_end_token_id": 248054,
|
| 111 |
-
"vision_start_token_id": 248053
|
| 112 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step13/generation_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"eos_token_id": 248046,
|
| 4 |
-
"output_attentions": false,
|
| 5 |
-
"output_hidden_states": false,
|
| 6 |
-
"pad_token_id": 248044,
|
| 7 |
-
"transformers_version": "5.5.0",
|
| 8 |
-
"use_cache": true
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step13/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4ec59196d188eda4c7db742d5bb9f3139a20b9ca9ede00f4885ec4fac4730d6f
|
| 3 |
-
size 10350019328
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step13/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step13/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
-
size 19989343
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step13/tokenizer_config.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 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 |
-
"model_max_length": 262144,
|
| 14 |
-
"model_specific_special_tokens": {
|
| 15 |
-
"audio_bos_token": "<|audio_start|>",
|
| 16 |
-
"audio_eos_token": "<|audio_end|>",
|
| 17 |
-
"audio_token": "<|audio_pad|>",
|
| 18 |
-
"image_token": "<|image_pad|>",
|
| 19 |
-
"video_token": "<|video_pad|>",
|
| 20 |
-
"vision_bos_token": "<|vision_start|>",
|
| 21 |
-
"vision_eos_token": "<|vision_end|>"
|
| 22 |
-
},
|
| 23 |
-
"pad_token": "<|endoftext|>",
|
| 24 |
-
"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+",
|
| 25 |
-
"processor_class": "Qwen3VLProcessor",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "TokenizersBackend",
|
| 28 |
-
"unk_token": null,
|
| 29 |
-
"video_token": "<|video_pad|>",
|
| 30 |
-
"vision_bos_token": "<|vision_start|>",
|
| 31 |
-
"vision_eos_token": "<|vision_end|>"
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/chat_template.jinja
DELETED
|
@@ -1,122 +0,0 @@
|
|
| 1 |
-
{%- set _enable_thinking = enable_thinking if enable_thinking is defined else none %}
|
| 2 |
-
{%- if tools %}
|
| 3 |
-
{{- '<|im_start|>system\n' }}
|
| 4 |
-
{%- if messages[0].role == 'system' %}
|
| 5 |
-
{%- if messages[0].content is string %}
|
| 6 |
-
{{- messages[0].content }}
|
| 7 |
-
{%- else %}
|
| 8 |
-
{%- for content in messages[0].content %}
|
| 9 |
-
{%- if 'text' in content %}
|
| 10 |
-
{{- content.text }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- endfor %}
|
| 13 |
-
{%- endif %}
|
| 14 |
-
{{- '\n\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{{- "# 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>" }}
|
| 17 |
-
{%- for tool in tools %}
|
| 18 |
-
{{- "\n" }}
|
| 19 |
-
{{- tool | tojson }}
|
| 20 |
-
{%- endfor %}
|
| 21 |
-
{{- "\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" }}
|
| 22 |
-
{%- else %}
|
| 23 |
-
{%- if messages[0].role == 'system' %}
|
| 24 |
-
{{- '<|im_start|>system\n' }}
|
| 25 |
-
{%- if messages[0].content is string %}
|
| 26 |
-
{{- messages[0].content }}
|
| 27 |
-
{%- else %}
|
| 28 |
-
{%- for content in messages[0].content %}
|
| 29 |
-
{%- if 'text' in content %}
|
| 30 |
-
{{- content.text }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- endfor %}
|
| 33 |
-
{%- endif %}
|
| 34 |
-
{{- '<|im_end|>\n' }}
|
| 35 |
-
{%- endif %}
|
| 36 |
-
{%- endif %}
|
| 37 |
-
{%- set image_count = namespace(value=0) %}
|
| 38 |
-
{%- set video_count = namespace(value=0) %}
|
| 39 |
-
{%- for message in messages %}
|
| 40 |
-
{%- if message.role == "user" %}
|
| 41 |
-
{{- '<|im_start|>' + message.role + '\n' }}
|
| 42 |
-
{%- if message.content is string %}
|
| 43 |
-
{{- message.content }}
|
| 44 |
-
{%- else %}
|
| 45 |
-
{%- for content in message.content %}
|
| 46 |
-
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 47 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 48 |
-
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 49 |
-
<|vision_start|><|image_pad|><|vision_end|>
|
| 50 |
-
{%- elif content.type == 'video' or 'video' in content %}
|
| 51 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 52 |
-
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 53 |
-
<|vision_start|><|video_pad|><|vision_end|>
|
| 54 |
-
{%- elif 'text' in content %}
|
| 55 |
-
{{- content.text }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endfor %}
|
| 58 |
-
{%- endif %}
|
| 59 |
-
{{- '<|im_end|>\n' }}
|
| 60 |
-
{%- elif message.role == "assistant" %}
|
| 61 |
-
{{- '<|im_start|>' + message.role + '\n' }}
|
| 62 |
-
{%- if message.content is string %}
|
| 63 |
-
{{- message.content }}
|
| 64 |
-
{%- else %}
|
| 65 |
-
{%- for content_item in message.content %}
|
| 66 |
-
{%- if 'text' in content_item %}
|
| 67 |
-
{{- content_item.text }}
|
| 68 |
-
{%- endif %}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
-
{%- if message.tool_calls %}
|
| 72 |
-
{%- for tool_call in message.tool_calls %}
|
| 73 |
-
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 74 |
-
{{- '\n' }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- if tool_call.function %}
|
| 77 |
-
{%- set tool_call = tool_call.function %}
|
| 78 |
-
{%- endif %}
|
| 79 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 80 |
-
{{- tool_call.name }}
|
| 81 |
-
{{- '", "arguments": ' }}
|
| 82 |
-
{%- if tool_call.arguments is string %}
|
| 83 |
-
{{- tool_call.arguments }}
|
| 84 |
-
{%- else %}
|
| 85 |
-
{{- tool_call.arguments | tojson }}
|
| 86 |
-
{%- endif %}
|
| 87 |
-
{{- '}\n</tool_call>' }}
|
| 88 |
-
{%- endfor %}
|
| 89 |
-
{%- endif %}
|
| 90 |
-
{{- '<|im_end|>\n' }}
|
| 91 |
-
{%- elif message.role == "tool" %}
|
| 92 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 93 |
-
{{- '<|im_start|>user' }}
|
| 94 |
-
{%- endif %}
|
| 95 |
-
{{- '\n<tool_response>\n' }}
|
| 96 |
-
{%- if message.content is string %}
|
| 97 |
-
{{- message.content }}
|
| 98 |
-
{%- else %}
|
| 99 |
-
{%- for content in message.content %}
|
| 100 |
-
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 101 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 102 |
-
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 103 |
-
<|vision_start|><|image_pad|><|vision_end|>
|
| 104 |
-
{%- elif content.type == 'video' or 'video' in content %}
|
| 105 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 106 |
-
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 107 |
-
<|vision_start|><|video_pad|><|vision_end|>
|
| 108 |
-
{%- elif 'text' in content %}
|
| 109 |
-
{{- content.text }}
|
| 110 |
-
{%- endif %}
|
| 111 |
-
{%- endfor %}
|
| 112 |
-
{%- endif %}
|
| 113 |
-
{{- '\n</tool_response>' }}
|
| 114 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 115 |
-
{{- '<|im_end|>\n' }}
|
| 116 |
-
{%- endif %}
|
| 117 |
-
{%- endif %}
|
| 118 |
-
{%- endfor %}
|
| 119 |
-
{%- if add_generation_prompt %}
|
| 120 |
-
{{- '<|im_start|>assistant\n' }}
|
| 121 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 122 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/config.json
DELETED
|
@@ -1,112 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3_5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": null,
|
| 6 |
-
"dtype": "float32",
|
| 7 |
-
"eos_token_id": 248046,
|
| 8 |
-
"image_token_id": 248056,
|
| 9 |
-
"model_type": "qwen3_5",
|
| 10 |
-
"pad_token_id": 248044,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"attn_output_gate": true,
|
| 15 |
-
"bos_token_id": null,
|
| 16 |
-
"dtype": "bfloat16",
|
| 17 |
-
"eos_token_id": 248044,
|
| 18 |
-
"full_attention_interval": 4,
|
| 19 |
-
"head_dim": 256,
|
| 20 |
-
"hidden_act": "silu",
|
| 21 |
-
"hidden_size": 2560,
|
| 22 |
-
"initializer_range": 0.02,
|
| 23 |
-
"intermediate_size": 9216,
|
| 24 |
-
"layer_types": [
|
| 25 |
-
"linear_attention",
|
| 26 |
-
"linear_attention",
|
| 27 |
-
"linear_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"linear_attention",
|
| 30 |
-
"linear_attention",
|
| 31 |
-
"linear_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"linear_attention",
|
| 34 |
-
"linear_attention",
|
| 35 |
-
"linear_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"linear_attention",
|
| 38 |
-
"linear_attention",
|
| 39 |
-
"linear_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"linear_attention",
|
| 42 |
-
"linear_attention",
|
| 43 |
-
"linear_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"linear_attention",
|
| 46 |
-
"linear_attention",
|
| 47 |
-
"linear_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"linear_attention",
|
| 50 |
-
"linear_attention",
|
| 51 |
-
"linear_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"linear_attention",
|
| 54 |
-
"linear_attention",
|
| 55 |
-
"linear_attention",
|
| 56 |
-
"full_attention"
|
| 57 |
-
],
|
| 58 |
-
"linear_conv_kernel_dim": 4,
|
| 59 |
-
"linear_key_head_dim": 128,
|
| 60 |
-
"linear_num_key_heads": 16,
|
| 61 |
-
"linear_num_value_heads": 32,
|
| 62 |
-
"linear_value_head_dim": 128,
|
| 63 |
-
"mamba_ssm_dtype": "float32",
|
| 64 |
-
"max_position_embeddings": 262144,
|
| 65 |
-
"mlp_only_layers": [],
|
| 66 |
-
"model_type": "qwen3_5_text",
|
| 67 |
-
"mtp_num_hidden_layers": 1,
|
| 68 |
-
"mtp_use_dedicated_embeddings": false,
|
| 69 |
-
"num_attention_heads": 16,
|
| 70 |
-
"num_hidden_layers": 32,
|
| 71 |
-
"num_key_value_heads": 4,
|
| 72 |
-
"pad_token_id": null,
|
| 73 |
-
"partial_rotary_factor": 0.25,
|
| 74 |
-
"rms_norm_eps": 1e-06,
|
| 75 |
-
"rope_parameters": {
|
| 76 |
-
"mrope_interleaved": true,
|
| 77 |
-
"mrope_section": [
|
| 78 |
-
11,
|
| 79 |
-
11,
|
| 80 |
-
10
|
| 81 |
-
],
|
| 82 |
-
"partial_rotary_factor": 0.25,
|
| 83 |
-
"rope_theta": 10000000,
|
| 84 |
-
"rope_type": "default"
|
| 85 |
-
},
|
| 86 |
-
"tie_word_embeddings": true,
|
| 87 |
-
"use_cache": true,
|
| 88 |
-
"vocab_size": 248320
|
| 89 |
-
},
|
| 90 |
-
"tie_word_embeddings": true,
|
| 91 |
-
"transformers_version": "5.5.0",
|
| 92 |
-
"video_token_id": 248057,
|
| 93 |
-
"vision_config": {
|
| 94 |
-
"deepstack_visual_indexes": [],
|
| 95 |
-
"depth": 24,
|
| 96 |
-
"dtype": "bfloat16",
|
| 97 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 98 |
-
"hidden_size": 1024,
|
| 99 |
-
"in_channels": 3,
|
| 100 |
-
"initializer_range": 0.02,
|
| 101 |
-
"intermediate_size": 4096,
|
| 102 |
-
"model_type": "qwen3_5",
|
| 103 |
-
"num_heads": 16,
|
| 104 |
-
"num_position_embeddings": 2304,
|
| 105 |
-
"out_hidden_size": 2560,
|
| 106 |
-
"patch_size": 16,
|
| 107 |
-
"spatial_merge_size": 2,
|
| 108 |
-
"temporal_patch_size": 2
|
| 109 |
-
},
|
| 110 |
-
"vision_end_token_id": 248054,
|
| 111 |
-
"vision_start_token_id": 248053
|
| 112 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/generation_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"eos_token_id": 248046,
|
| 4 |
-
"output_attentions": false,
|
| 5 |
-
"output_hidden_states": false,
|
| 6 |
-
"pad_token_id": 248044,
|
| 7 |
-
"transformers_version": "5.5.0",
|
| 8 |
-
"use_cache": true
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:02584dd0b151f62c8eb5eadbd6e703e29d08c884c57ab67ecb745083af6f88d3
|
| 3 |
-
size 10350019328
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/processor_config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
-
size 19989343
|
|
|
|
|
|
|
|
|
|
|
|
cv40-60-patch2/step26/tokenizer_config.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 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 |
-
"model_max_length": 262144,
|
| 14 |
-
"model_specific_special_tokens": {
|
| 15 |
-
"audio_bos_token": "<|audio_start|>",
|
| 16 |
-
"audio_eos_token": "<|audio_end|>",
|
| 17 |
-
"audio_token": "<|audio_pad|>",
|
| 18 |
-
"image_token": "<|image_pad|>",
|
| 19 |
-
"video_token": "<|video_pad|>",
|
| 20 |
-
"vision_bos_token": "<|vision_start|>",
|
| 21 |
-
"vision_eos_token": "<|vision_end|>"
|
| 22 |
-
},
|
| 23 |
-
"pad_token": "<|endoftext|>",
|
| 24 |
-
"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+",
|
| 25 |
-
"processor_class": "Qwen3VLProcessor",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "TokenizersBackend",
|
| 28 |
-
"unk_token": null,
|
| 29 |
-
"video_token": "<|video_pad|>",
|
| 30 |
-
"vision_bos_token": "<|vision_start|>",
|
| 31 |
-
"vision_eos_token": "<|vision_end|>"
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|