|
{ |
|
"model_class": "FineTuneTrainCogAgentModel", |
|
"tokenizer_type": "vicuna-7b-v1.5", |
|
"num_layers": 32, |
|
"hidden_size": 4096, |
|
"num_attention_heads": 32, |
|
"vocab_size": 32000, |
|
"layernorm_order": "pre", |
|
"model_parallel_size": 1, |
|
"max_sequence_length": 4096, |
|
"is_decoder": [ |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true, |
|
true |
|
], |
|
"cross_attn_hidden_size": 1024, |
|
"use_bias": false, |
|
"inner_hidden_size": 11008, |
|
"cross_hidden_size_per_attention_head": 32, |
|
"pre_seq_len": 8, |
|
"lora_rank": 50, |
|
"use_ptuning": false, |
|
"use_lora": false, |
|
"use_qlora": false, |
|
"layer_range": null, |
|
"image_length": 256, |
|
"cross_image_pix": 1120, |
|
"eva_args": { |
|
"model_class": "EVA2CLIPModel", |
|
"num_layers": 63, |
|
"hidden_size": 1792, |
|
"num_attention_heads": 16, |
|
"vocab_size": 1, |
|
"layernorm_order": "post", |
|
"model_parallel_size": 1, |
|
"max_sequence_length": 257, |
|
"inner_hidden_size": 15360, |
|
"use_final_layernorm": false, |
|
"layernorm_epsilon": 1e-06, |
|
"row_parallel_linear_final_bias": false, |
|
"image_size": [ |
|
224, |
|
224 |
|
], |
|
"pre_len": 1, |
|
"post_len": 0, |
|
"in_channels": 3, |
|
"patch_size": 14 |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"pad_token_id": 0 |
|
} |