File size: 5,512 Bytes
cc3c1ed |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 |
{
"_name_or_path": "/models//cogvlm2-llama3-chat-19B",
"architectures": [
"CogVLMForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_cogvlm.CogVLMConfig",
"AutoModelForCausalLM": "modeling_cogvlm.CogVLMForCausalLM"
},
"bos_token_id": 128000,
"eos_token_id": [
128001,
128009
],
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_multi_query_heads": 8,
"pad_token_id": 128002,
"quantization_config": {
"amp": true,
"autoround_version": "0.4.0.dev",
"backend": "auto_round:gptq:exllamav2",
"batch_size": 1,
"bits": 4,
"data_type": "int",
"dataset": "liuhaotian/llava_conv_58k",
"enable_minmax_tuning": true,
"enable_norm_bias_tuning": false,
"enable_quanted_input": true,
"gradient_accumulate_steps": 4,
"group_size": 128,
"iters": 200,
"low_gpu_mem_usage": false,
"lr": 0.005,
"minmax_lr": 0.005,
"nsamples": 128,
"quant_method": "intel/auto-round",
"scale_dtype": "torch.float16",
"seqlen": 512,
"sym": true,
"to_quant_block_names": [
[
"model.layers.0",
"model.layers.1",
"model.layers.2",
"model.layers.3",
"model.layers.4",
"model.layers.5",
"model.layers.6",
"model.layers.7",
"model.layers.8",
"model.layers.9",
"model.layers.10",
"model.layers.11",
"model.layers.12",
"model.layers.13",
"model.layers.14",
"model.layers.15",
"model.layers.16",
"model.layers.17",
"model.layers.18",
"model.layers.19",
"model.layers.20",
"model.layers.21",
"model.layers.22",
"model.layers.23",
"model.layers.24",
"model.layers.25",
"model.layers.26",
"model.layers.27",
"model.layers.28",
"model.layers.29",
"model.layers.30",
"model.layers.31"
],
[
"model.vision.transformer.layers.0",
"model.vision.transformer.layers.1",
"model.vision.transformer.layers.2",
"model.vision.transformer.layers.3",
"model.vision.transformer.layers.4",
"model.vision.transformer.layers.5",
"model.vision.transformer.layers.6",
"model.vision.transformer.layers.7",
"model.vision.transformer.layers.8",
"model.vision.transformer.layers.9",
"model.vision.transformer.layers.10",
"model.vision.transformer.layers.11",
"model.vision.transformer.layers.12",
"model.vision.transformer.layers.13",
"model.vision.transformer.layers.14",
"model.vision.transformer.layers.15",
"model.vision.transformer.layers.16",
"model.vision.transformer.layers.17",
"model.vision.transformer.layers.18",
"model.vision.transformer.layers.19",
"model.vision.transformer.layers.20",
"model.vision.transformer.layers.21",
"model.vision.transformer.layers.22",
"model.vision.transformer.layers.23",
"model.vision.transformer.layers.24",
"model.vision.transformer.layers.25",
"model.vision.transformer.layers.26",
"model.vision.transformer.layers.27",
"model.vision.transformer.layers.28",
"model.vision.transformer.layers.29",
"model.vision.transformer.layers.30",
"model.vision.transformer.layers.31",
"model.vision.transformer.layers.32",
"model.vision.transformer.layers.33",
"model.vision.transformer.layers.34",
"model.vision.transformer.layers.35",
"model.vision.transformer.layers.36",
"model.vision.transformer.layers.37",
"model.vision.transformer.layers.38",
"model.vision.transformer.layers.39",
"model.vision.transformer.layers.40",
"model.vision.transformer.layers.41",
"model.vision.transformer.layers.42",
"model.vision.transformer.layers.43",
"model.vision.transformer.layers.44",
"model.vision.transformer.layers.45",
"model.vision.transformer.layers.46",
"model.vision.transformer.layers.47",
"model.vision.transformer.layers.48",
"model.vision.transformer.layers.49",
"model.vision.transformer.layers.50",
"model.vision.transformer.layers.51",
"model.vision.transformer.layers.52",
"model.vision.transformer.layers.53",
"model.vision.transformer.layers.54",
"model.vision.transformer.layers.55",
"model.vision.transformer.layers.56",
"model.vision.transformer.layers.57",
"model.vision.transformer.layers.58",
"model.vision.transformer.layers.59",
"model.vision.transformer.layers.60",
"model.vision.transformer.layers.61",
"model.vision.transformer.layers.62"
]
]
},
"rms_norm_eps": 1e-05,
"template_version": "chat",
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.2",
"use_cache": true,
"vision_config": {
"dropout_prob": 0.0,
"hidden_act": "gelu",
"hidden_size": 1792,
"image_size": 1344,
"in_channels": 3,
"intermediate_size": 15360,
"layer_norm_eps": 1e-06,
"num_heads": 16,
"num_hidden_layers": 63,
"num_positions": 9217,
"patch_size": 14
},
"vocab_size": 128256
}
|