lr3e-4 / config.json
leejuhyoeng's picture
Training in progress, step 1413
606dffe verified
{
"_name_or_path": "Salesforce/blip2-opt-2.7b",
"architectures": [
"Blip2ForConditionalGeneration"
],
"initializer_factor": 1.0,
"initializer_range": 0.02,
"model_type": "blip-2",
"num_query_tokens": 32,
"qformer_config": {
"classifier_dropout": null,
"model_type": "blip_2_qformer"
},
"text_config": {
"_name_or_path": "heegyu/kogpt-j-350m",
"activation_function": "gelu_new",
"architectures": [
"GPTJForCausalLM"
],
"attn_pdrop": 0.1,
"bos_token_id": 1,
"embd_pdrop": 0.1,
"eos_token_id": 2,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gptj",
"n_embd": 1024,
"n_head": 16,
"n_inner": null,
"n_layer": 20,
"n_positions": 1024,
"pad_token_id": 0,
"resid_pdrop": 0.0,
"rotary_dim": 32,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"tie_word_embeddings": false,
"tokenizer_class": "GPT2Tokenizer",
"torch_dtype": "float32",
"unk_token_id": 5,
"vocab_size": 51200
},
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"use_decoder_only_language_model": true,
"vision_config": {
"dropout": 0.0,
"initializer_factor": 1.0,
"model_type": "blip_2_vision_model",
"num_channels": 3,
"projection_dim": 512
}
}