ggcristian commited on
Commit
2c3315f
·
verified ·
1 Parent(s): 6a101d7

Update weights and model card

Browse files
.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
INTRO.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Qwen3.5-9B-RL-Verif
2
+
3
+ A fine-tune of [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for SystemVerilog design verification: RTL → Test-Plan, (RTL, Test-Plan) → Testbench, and adding functional checks to an existing stimulus testbench. Training combines Gemma-4-31B distillation with reinforcement learning from verifiable rewards, targeting testbenches that pass on the golden DUT and reject faulty variants.
4
+
5
+ Access to the model and this detailed card is gated while the paper is under peer review.
6
+
7
+ 🤗 **Models**
8
+
9
+ - [Qwen3.6-27B-RL-Verif](https://huggingface.co/HPAI-BSC/Qwen3.6-27B-RL-Verif)
10
+ - [Qwen3.5-9B-RL-Verif](https://huggingface.co/HPAI-BSC/Qwen3.5-9B-RL-Verif) ← you are here
11
+
12
+ 🤗 **Datasets**
13
+
14
+ - [SystemVerilog-SFT-86k](https://huggingface.co/datasets/HPAI-BSC/SystemVerilog-SFT-86k)
15
+ - [SystemVerilog-RL-12k](https://huggingface.co/datasets/HPAI-BSC/SystemVerilog-RL-12k)
16
+
17
+ ## Evaluation
18
+
19
+ The results below are reported in the paper. Pass@1 is estimated from five samples per problem. All models are evaluated with vLLM under the same scoring flow.
20
+
21
+ ### CVDP v1.1.0 Non-agentic design verification
22
+
23
+ | Model | Stimulus (cid012) | Checking (cid013) | Assertion (cid014) | Debug (cid016) |
24
+ | --- | ---: | ---: | ---: | ---: |
25
+ | Kimi-K2.5 | 22.1% | 23.4% | 36.1% | 64.6% |
26
+ | GLM-5.2-FP8 | 34.0% | 14.0% | 33.1% | 44.6% |
27
+ | DeepSeek-V4-Flash-0731 | 22.1% | 18.5% | 28.1% | **65.1%** |
28
+ | Gemma-4-31B | 24.8% | 17.7% | 33.1% | 63.4% |
29
+ | Qwen3.6-27B | 19.4% | 15.1% | 22.4% | 58.9% |
30
+ | Qwen3.5-9B | 3.0% | 1.9% | 4.8% | 22.9% |
31
+ | Our 9B model | 29.5% | 23.0% | 15.8% | 29.1% |
32
+ | Our 27B model | **37.0%** | **36.2%** | **42.4%** | 60.6% |
33
+
34
+ ### CVDP v1.1.0 Heavy Agentic design verification
35
+
36
+ Although training uses single-turn tasks, the models are also evaluated with OpenCode as a coding-agent harness, without a custom evaluator-feedback loop.
37
+
38
+ | Model | Stimulus (cid012) | Checking (cid013) | Assertion (cid014) | Debug (cid016) |
39
+ |---|---:|---:|---:|---:|
40
+ | Kimi-K2.5 | 37.5% | 40.0% | 37.1% | 54.6% |
41
+ | GLM-5.2-FP8 | 52.5% | 22.9% | **60.0%** | **58.6%** |
42
+ | DeepSeek-V4-Flash-0731 | **65.0%** | 34.3% | 51.4% | 57.9% |
43
+ | Gemma-4-31B | 17.5% | 14.3% | 22.9% | 31.8% |
44
+ | Qwen3.6-27B | 32.5% | 17.1% | 20.0% | 46.8% |
45
+ | Qwen3.5-9B | 5.0% | 0.0% | 5.7% | 18.6% |
46
+ | Our 9B model | 25.0% | 11.4% | 20.0% | 24.6% |
47
+ | Our 27B model | **65.0%** | **42.9%** | 31.4% | 46.4% |
48
+
49
+ ### AutoEval-ECov
50
+
51
+ AutoEval-ECov reformulates 156 VerilogEval problems as a testbench stimulus-generation benchmark. Given a specification and the DUT source, the model must generate a testbench that reaches 100% target coverage.
52
+
53
+ | Model | Pass@1 |
54
+ |---|---:|
55
+ | Kimi-K2.5 | 37.1% |
56
+ | GLM-5.2-FP8 | 81.5% |
57
+ | DeepSeek-V4-Flash-0731 | 43.5% |
58
+ | Gemma-4-31B | 77.7% |
59
+ | Qwen3.6-27B | 56.7% |
60
+ | Qwen3.5-9B | 3.2% |
61
+ | Our 9B model | 79.5% |
62
+ | Our 27B model | **84.7%** |
63
+
64
+ ### Evaluation scope
65
+
66
+ [CVDP](https://github.com/NVlabs/cvdp_benchmark) v1.1.0 stimulus, checking, and assertion scoring is ported from commercial EDA tools to Verilator. AutoEval-ECov is evaluated with the same open-source approach; debugging retains CVDP's original open-source flow. These results are not directly comparable with scores from the commercial flow. Assertion scores are upper-bound estimates because Verilator does not fully support assertion coverage.
67
+
68
+ ## Contact
69
+
70
+ [cristian.gutierrez@bsc.es](mailto:cristian.gutierrez@bsc.es)
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Qwen3.5-9B-RL-Verif
2
+
3
+ Access is gated while the paper is under peer review. After your access request is approved, see [INTRO.md](https://huggingface.co/HPAI-BSC/Qwen3.5-9B-RL-Verif/blob/main/INTRO.md) for the model introduction and evaluation results.
4
+
5
+ 🤗 **Models**
6
+
7
+ - [Qwen3.6-27B-RL-Verif](https://huggingface.co/HPAI-BSC/Qwen3.6-27B-RL-Verif)
8
+ - [Qwen3.5-9B-RL-Verif](https://huggingface.co/HPAI-BSC/Qwen3.5-9B-RL-Verif) ← you are here
9
+
10
+ 🤗 **Datasets**
11
+
12
+ - [SystemVerilog-SFT-86k](https://huggingface.co/datasets/HPAI-BSC/SystemVerilog-SFT-86k)
13
+ - [SystemVerilog-RL-12k](https://huggingface.co/datasets/HPAI-BSC/SystemVerilog-RL-12k)
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\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>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_type": "qwen3_5",
9
+ "pad_token_id": 248044,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "attn_output_gate": true,
14
+ "bos_token_id": null,
15
+ "dtype": "bfloat16",
16
+ "eos_token_id": 248044,
17
+ "full_attention_interval": 4,
18
+ "head_dim": 256,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 4096,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 12288,
23
+ "layer_types": [
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention"
56
+ ],
57
+ "linear_conv_kernel_dim": 4,
58
+ "linear_key_head_dim": 128,
59
+ "linear_num_key_heads": 16,
60
+ "linear_num_value_heads": 32,
61
+ "linear_value_head_dim": 128,
62
+ "mamba_ssm_dtype": "float32",
63
+ "max_position_embeddings": 262144,
64
+ "mlp_only_layers": [],
65
+ "model_type": "qwen3_5_text",
66
+ "mtp_num_hidden_layers": 1,
67
+ "mtp_use_dedicated_embeddings": false,
68
+ "num_attention_heads": 16,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 4,
71
+ "pad_token_id": null,
72
+ "partial_rotary_factor": 0.25,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_parameters": {
75
+ "mrope_interleaved": true,
76
+ "mrope_section": [
77
+ 11,
78
+ 11,
79
+ 10
80
+ ],
81
+ "partial_rotary_factor": 0.25,
82
+ "rope_theta": 10000000,
83
+ "rope_type": "default"
84
+ },
85
+ "tie_word_embeddings": false,
86
+ "use_cache": true,
87
+ "vocab_size": 248320
88
+ },
89
+ "tie_word_embeddings": false,
90
+ "transformers_version": "5.10.2",
91
+ "use_cache": false,
92
+ "video_token_id": 248057,
93
+ "vision_config": {
94
+ "deepstack_visual_indexes": [],
95
+ "depth": 27,
96
+ "dtype": "bfloat16",
97
+ "hidden_act": "gelu_pytorch_tanh",
98
+ "hidden_size": 1152,
99
+ "in_channels": 3,
100
+ "initializer_range": 0.02,
101
+ "intermediate_size": 4304,
102
+ "model_type": "qwen3_5_vision",
103
+ "num_heads": 16,
104
+ "num_position_embeddings": 2304,
105
+ "out_hidden_size": 4096,
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
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248044
6
+ ],
7
+ "pad_token_id": 248044,
8
+ "transformers_version": "5.10.2",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66d2c60404ddbce2086d39c2346931496bbc18416534ea36614b757d316579e
3
+ size 18819722392
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
+ }
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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+",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }
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
+ }