Hugging Face's logo

Reza2kn
/
Bina-0.1-Koochik

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
ocr
persian
vision-language
conversational
Model card Files
xet
 Community
2
Reza2kn commited on
Commit
0a96e99
·
verified ·
1 Parent(s): 1e6a562

Publish merged BF16 Bina 0.1 step 8000

Browse files
Files changed (7) hide show
  1. chat_template.jinja +66 -0
  2. config.json +102 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. processor_config.json +63 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +24 -0
chat_template.jinja ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 messages[0].role == 'system' %}
46
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
47
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
48
+ {%- endif %}
49
+ {%- for message in messages %}
50
+ {%- set content = render_content(message.content, true)|trim %}
51
+ {%- if message.role == "system" %}
52
+ {%- if not loop.first %}
53
+ {{- raise_exception('System message must be at the beginning.') }}
54
+ {%- endif %}
55
+ {%- elif message.role == "user" %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
57
+ {%- elif message.role == "assistant" %}
58
+ {{- '<|im_start|>' + message.role + '\n' + content }}
59
+ {{- '<|im_end|>\n' }}
60
+ {%- else %}
61
+ {{- raise_exception('Unexpected message role.') }}
62
+ {%- endif %}
63
+ {%- endfor %}
64
+ {%- if add_generation_prompt %}
65
+ {{- '<|im_start|>assistant\n' }}
66
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 11,
7
+ "model_type": "qwen3_5",
8
+ "num_nextn_predict_layers": 1,
9
+ "text_config": {
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "attn_output_gate": true,
13
+ "bos_token_id": null,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 248044,
16
+ "full_attention_interval": 4,
17
+ "head_dim": 256,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3584,
22
+ "layer_types": [
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "full_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention"
47
+ ],
48
+ "linear_conv_kernel_dim": 4,
49
+ "linear_key_head_dim": 128,
50
+ "linear_num_key_heads": 16,
51
+ "linear_num_value_heads": 16,
52
+ "linear_value_head_dim": 128,
53
+ "mamba_ssm_dtype": "float32",
54
+ "max_position_embeddings": 262144,
55
+ "mlp_only_layers": [],
56
+ "model_type": "qwen3_5_text",
57
+ "mtp_num_hidden_layers": 1,
58
+ "mtp_use_dedicated_embeddings": false,
59
+ "num_attention_heads": 8,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "pad_token_id": null,
63
+ "partial_rotary_factor": 0.25,
64
+ "rms_norm_eps": 1e-06,
65
+ "rope_parameters": {
66
+ "mrope_interleaved": true,
67
+ "mrope_section": [
68
+ 11,
69
+ 11,
70
+ 10
71
+ ],
72
+ "partial_rotary_factor": 0.25,
73
+ "rope_theta": 10000000,
74
+ "rope_type": "default"
75
+ },
76
+ "tie_word_embeddings": true,
77
+ "use_cache": true,
78
+ "vocab_size": 65425
79
+ },
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.3.0",
82
+ "video_token_id": 12,
83
+ "vision_config": {
84
+ "deepstack_visual_indexes": [],
85
+ "depth": 12,
86
+ "dtype": "bfloat16",
87
+ "hidden_act": "gelu_pytorch_tanh",
88
+ "hidden_size": 768,
89
+ "in_channels": 3,
90
+ "initializer_range": 0.02,
91
+ "intermediate_size": 3072,
92
+ "model_type": "qwen3_5",
93
+ "num_heads": 12,
94
+ "num_position_embeddings": 2304,
95
+ "out_hidden_size": 1024,
96
+ "patch_size": 16,
97
+ "spatial_merge_size": 2,
98
+ "temporal_patch_size": 2
99
+ },
100
+ "vision_end_token_id": 10,
101
+ "vision_start_token_id": 9
102
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 2,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "5.3.0",
6
+ "use_cache": true
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2193be4ef3d2366438121a15b7a1dea2bb85b24f83145e5a39bfa1f387891ada
3
+ size 1331461328
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 234881024,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": null,
4
+ "eos_token": "<|im_end|>",
5
+ "extra_special_tokens": [
6
+ "<|im_start|>",
7
+ "<|object_ref_start|>",
8
+ "<|object_ref_end|>",
9
+ "<|box_start|>",
10
+ "<|box_end|>",
11
+ "<|quad_start|>",
12
+ "<|quad_end|>",
13
+ "<|vision_start|>",
14
+ "<|vision_end|>",
15
+ "<|image_pad|>",
16
+ "<|video_pad|>"
17
+ ],
18
+ "is_local": false,
19
+ "model_max_length": 1000000000000000019884624838656,
20
+ "pad_token": "<|endoftext|>",
21
+ "processor_class": "Qwen3VLProcessor",
22
+ "tokenizer_class": "TokenizersBackend",
23
+ "unk_token": "<unk>"
24
+ }