File size: 1,813 Bytes
0fb6b45 |
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 |
{
"model_class": "FineTuneVisualGLMModel",
"tokenizer_type": "THUDM/chatglm-6b",
"num_layers": 28,
"hidden_size": 4096,
"num_attention_heads": 32,
"vocab_size": 130528,
"layernorm_order": "post",
"model_parallel_size": 1,
"max_sequence_length": 2048,
"pre_seq_len": 4,
"lora_rank": 32,
"use_ptuning": false,
"use_lora": true,
"use_qlora": false,
"layer_range": [],
"image_length": 32,
"eva_args": {
"num_layers": 39,
"hidden_size": 1408,
"num_attention_heads": 16,
"vocab_size": 1,
"layernorm_order": "pre",
"model_parallel_size": 1,
"max_sequence_length": 257,
"inner_hidden_size": 6144,
"use_final_layernorm": false,
"layernorm_epsilon": 1e-06,
"image_size": [
224,
224
],
"pre_len": 1,
"post_len": 0,
"in_channels": 3,
"num_classes": 0,
"patch_size": 14
},
"qformer_args": {
"num_layers": 12,
"hidden_size": 768,
"num_attention_heads": 12,
"vocab_size": 32,
"layernorm_order": "post",
"model_parallel_size": 1,
"max_sequence_length": 0,
"is_decoder": [
true,
false,
true,
false,
true,
false,
true,
false,
true,
false,
true,
false
],
"cross_attn_hidden_size": 1408,
"layernorm_epsilon": 1e-12
},
"bos_token_id": 130004,
"mask_token_id": 130000,
"gmask_token_id": 130001,
"pad_token_id": 3,
"image_size": [
224,
224
],
"pre_len": 1,
"post_len": 0,
"in_channels": 3,
"patch_size": 14
} |