File size: 3,211 Bytes
a0b5907 45a3074 a0b5907 |
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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
{
"architectures": [
"TinyLlavaForConditionalGeneration"
],
"cache_dir": null,
"connector_type": "mlp2x_gelu",
"hidden_size": 1536,
"ignore_index": -100,
"image_aspect_ratio": "square",
"image_token_index": -200,
"llm_model_name_or_path": "apple/OpenELM-450M-Instruct",
"model_type": "tinyllava",
"auto_map": {
"AutoConfig": "configuration.TinyLlavaConfig",
"AutoModelForCausalLM": "modeling_tinyllava_elm.TinyLlavaForConditionalGeneration"
},
"num_queries": 128,
"num_resampler_layers": 3,
"pad_token": "<unk>",
"pad_token_id": 0,
"resampler_hidden_size": 768,
"text_config": {
"_name_or_path": "apple/OpenELM-450M-Instruct",
"activation_fn_name": "swish",
"architectures": [
"OpenELMForCausalLM"
],
"auto_map": {
"AutoConfig": "apple/OpenELM-450M-Instruct--configuration_openelm.OpenELMConfig",
"AutoModelForCausalLM": "apple/OpenELM-450M-Instruct--modeling_openelm.OpenELMForCausalLM"
},
"ffn_dim_divisor": 256,
"ffn_multipliers": [
0.5,
0.68,
0.87,
1.05,
1.24,
1.42,
1.61,
1.79,
1.97,
2.16,
2.34,
2.53,
2.71,
2.89,
3.08,
3.26,
3.45,
3.63,
3.82,
4.0
],
"ffn_with_glu": true,
"head_dim": 64,
"max_context_length": 2048,
"model_dim": 1536,
"model_type": "openelm",
"normalization_layer_name": "rms_norm",
"normalize_qk_projections": true,
"num_gqa_groups": 4,
"num_kv_heads": [
3,
3,
3,
4,
4,
4,
4,
4,
4,
4,
5,
5,
5,
5,
5,
5,
6,
6,
6,
6
],
"num_query_heads": [
12,
12,
12,
16,
16,
16,
16,
16,
16,
16,
20,
20,
20,
20,
20,
20,
24,
24,
24,
24
],
"num_transformer_layers": 20,
"qkv_multipliers": [
0.5,
1.0
],
"rope_freq_constant": 10000,
"rope_max_length": 4096,
"share_input_output_layers": true,
"tie_word_embeddings": true,
"torch_dtype": "float16"
},
"tokenizer_model_max_length": 2048,
"tokenizer_name_or_path": "meta-llama/Llama-2-7b-hf",
"tokenizer_padding_side": "right",
"tokenizer_use_fast": false,
"torch_dtype": "float16",
"transformers_version": "4.39.3",
"tune_type_connector": "full",
"tune_type_llm": "full",
"tune_type_vision_tower": "frozen",
"tune_vision_tower_from_layer": 0,
"use_cache": true,
"vision_config": {
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_name_or_path": "google/siglip-so400m-patch14-384",
"model_name_or_path2": "",
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14
},
"vision_feature_layer": -2,
"vision_feature_select_strategy": "patch",
"vision_hidden_size": 1152,
"vision_model_name_or_path": "google/siglip-so400m-patch14-384",
"vision_model_name_or_path2": "",
"vocab_size": 32000
}
|