File size: 1,446 Bytes
9b1702f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "_name_or_path": "lmsys/vicuna-7b-v1.5",
    "architectures": [
        "LlavaLlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "freeze_mm_mlp_adapter": false,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "image_aspect_ratio": "pad",
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 4096,
    "mm_hidden_size": 1024,
    "mm_patch_merge_type": "flat",
    "mm_projector_lr": null,
    "mm_projector_type": "mlp2x_gelu",
    "mm_use_im_patch_token": false,
    "mm_use_im_start_end": false,
    "mm_vision_select_feature": "patch",
    "mm_vision_select_layer": -2,
    "mm_vision_tower": "openai/clip-vit-large-patch14-336",
    "model_type": "llava_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,
    "tokenizer_model_max_length": 2048,
    "tokenizer_padding_side": "right",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.37.2",
    "tune_mm_mlp_adapter": false,
    "use_cache": true,
    "use_mm_proj": true,
    "vocab_size": 32000,
    "encoder_version": "v1",
    "num_learnable_tokens": 0,
    "mm_text_select_layer": -2,
    "mm_text_select_feature": "cls_patch"
}