File size: 1,262 Bytes
d7bdf82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
672f3b8
d7bdf82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "architectures": [
    "VisionLanguagePreTrainedModel"
  ],
  "language_model_config": {
    "_name_or_path": "vicuna-7b-v1.5",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "use_cache": true,
    "vocab_size": 32064
  },
  "model_type": "vision_language_model",
  "projector_config": {
    "hidden_act": "gelu",
    "in_features": 1024,
    "model_type": "llava_next_projector",
    "out_features": 4096
  },
  "torch_dtype": "float16",
  "transformers_version": "4.40.0.dev0",
  "vision_tower_config": {
    "model_type": "clip_vision_tower",
    "pretrained_model_name_or_path": "openai/clip-vit-large-patch14-336",
    "select_feature": "patch",
    "select_layer": -2
  }
}