| { | |
| "_name_or_path": "bingwork/MMAlaya", | |
| "architectures": [ | |
| "MMAlayaMPTForCausalLM" | |
| ], | |
| "attn_config": { | |
| "alibi": true, | |
| "alibi_bias_max": 8, | |
| "attn_impl": "torch", | |
| "attn_pdrop": 0.0, | |
| "attn_type": "multihead_attention", | |
| "attn_uses_sequence_id": false, | |
| "clip_qkv": null, | |
| "prefix_lm": false, | |
| "qk_ln": false, | |
| "softmax_scale": null | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_mmalaya.MMAlayaMPTConfig", | |
| "AutoModelForCausalLM": "modeling_mmalaya.MMAlayaMPTForCausalLM" | |
| }, | |
| "d_model": 4096, | |
| "emb_pdrop": 0.0, | |
| "embedding_fraction": 1.0, | |
| "expansion_ratio": 4, | |
| "fc_type": "torch", | |
| "ffn_config": { | |
| "fc_type": "torch", | |
| "ffn_type": "mptmlp" | |
| }, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_size": 4096, | |
| "image_aspect_ratio": "square", | |
| "init_config": { | |
| "emb_init_std": null, | |
| "emb_init_uniform_lim": null, | |
| "fan_mode": "fan_in", | |
| "init_div_is_residual": true, | |
| "init_gain": 0.0, | |
| "init_nonlinearity": "relu", | |
| "init_std": null, | |
| "name": "kaiming_normal_", | |
| "verbose": 0 | |
| }, | |
| "init_device": "cpu", | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "learned_pos_emb": false, | |
| "logit_scale": null, | |
| "max_seq_len": 2048, | |
| "mm_hidden_size": 768, | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "linear", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -1, | |
| "model_type": "mmalaya", | |
| "n_heads": 32, | |
| "n_layers": 32, | |
| "no_bias": false, | |
| "norm_type": "low_precision_layernorm", | |
| "num_query_tokens": 32, | |
| "qformer_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_probs_dropout_prob": 0.1, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "classifier_dropout": null, | |
| "cross_attention_frequency": 2, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_hidden_size": 1408, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 512, | |
| "min_length": 0, | |
| "model_type": "blip_2_qformer", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "transformers_version": "4.27.0.dev0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vocab_size": 30522 | |
| }, | |
| "resid_pdrop": 0.0, | |
| "tokenizer_model_max_length": 2048, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.33.3", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": true, | |
| "use_decoder_only_language_model": true, | |
| "use_mm_proj": true, | |
| "verbose": 0, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dropout": 0.0, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1408, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 224, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 1e-10, | |
| "intermediate_size": 6144, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "blip_2_vision_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 39, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "prefix": null, | |
| "problem_type": null, | |
| "projection_dim": 512, | |
| "pruned_heads": {}, | |
| "qkv_bias": true, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "transformers_version": "4.27.0.dev0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "vocab_size": 60160 | |
| } | |