Hugging Face's logo

Ertugrul
/
Qwen2-VL-7B-Captioner-Relaxed

Image-to-Text
Transformers
Safetensors
English
qwen2_vl
image-text-to-text
text-generation-inference
Inference Endpoints
Model card Files Community
1
Ertugrul commited on
Commit
20d6cd1
•
1 Parent(s): cc244c8

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +46 -47
config.json CHANGED
@@ -1,47 +1,46 @@
1
- {
2
- "_name_or_path": "Ertugrul/Qwen2-VL-7B-Captioner-Relaxed",
3
- "architectures": [
4
- "Qwen2VLForConditionalGeneration"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 3584,
11
- "image_token_id": 151655,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 18944,
14
- "max_position_embeddings": 32768,
15
- "max_window_layers": 28,
16
- "model_type": "qwen2_vl",
17
- "num_attention_heads": 28,
18
- "num_hidden_layers": 28,
19
- "num_key_value_heads": 4,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": {
22
- "mrope_section": [
23
- 16,
24
- 24,
25
- 24
26
- ],
27
- "rope_type": "default",
28
- "type": "default"
29
- },
30
- "rope_theta": 1000000.0,
31
- "sliding_window": 32768,
32
- "tie_word_embeddings": false,
33
- "torch_dtype": "bfloat16",
34
- "transformers_version": "4.45.0.dev0",
35
- "use_cache": false,
36
- "use_sliding_window": false,
37
- "video_token_id": 151656,
38
- "vision_config": {
39
- "in_chans": 3,
40
- "model_type": "qwen2_vl",
41
- "spatial_patch_size": 14
42
- },
43
- "vision_end_token_id": 151653,
44
- "vision_start_token_id": 151652,
45
- "vision_token_id": 151654,
46
- "vocab_size": 152064
47
- }
 
1
+ {
2
+ "_name_or_path": "Ertugrul/Qwen2-VL-7B-Captioner-Relaxed",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "type": "mrope",
23
+ "mrope_section": [
24
+ 16,
25
+ 24,
26
+ 24
27
+ ]
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.0.dev0",
34
+ "use_cache": false,
35
+ "use_sliding_window": false,
36
+ "video_token_id": 151656,
37
+ "vision_config": {
38
+ "in_chans": 3,
39
+ "model_type": "qwen2_vl",
40
+ "spatial_patch_size": 14
41
+ },
42
+ "vision_end_token_id": 151653,
43
+ "vision_start_token_id": 151652,
44
+ "vision_token_id": 151654,
45
+ "vocab_size": 152064
46
+ }