File size: 1,448 Bytes
026a06c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
{
  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-random-llava-next/config.json",
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      30,
      60
    ],
    [
      60,
      30
    ],
    [
      60,
      60
    ],
    [
      90,
      30
    ],
    [
      30,
      90
    ]
  ],
  "image_token_index": 32000,
  "model_type": "llava_next",
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "bos_token_id": 0,
    "eos_token_id": 1,
    "hidden_size": 16,
    "intermediate_size": 64,
    "model_type": "llama",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 4,
    "pad_token_id": 3201,
    "torch_dtype": "float32",
    "vocab_size": 32002
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "use_image_newline_parameter": true,
  "vision_config": {
    "attention_dropout": 0.1,
    "dropout": 0.1,
    "hidden_size": 32,
    "image_size": 30,
    "intermediate_size": 37,
    "model_type": "clip_vision_model",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "patch_size": 2,
    "projection_dim": 32
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default",
  "vocab_size": 32002
}