| { | |
| "_commit_hash": null, | |
| "_name_or_path": "hustvl/mmMamba_hybrid", | |
| "architectures": [ | |
| "mmMambaChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_mmMamba_chat.mmMambaChatConfig", | |
| "AutoModel": "modeling_mmMamba_chat.mmMambaChatModel", | |
| "AutoModelForCausalLM": "modeling_mmMamba_chat.mmMambaChatModel" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": true, | |
| "embedding_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "flash_attention_2", | |
| "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, | |
| "downsample_ratio": 0.5, | |
| "drop_path_rate": 0.0, | |
| "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": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 448, | |
| "img_context_token_id": 92546, | |
| "initializer_factor": 1e-05, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layers_block_type":["mha", "mamba2", "mamba2", "mamba2", "mha", "mamba2", "mamba2", "mamba2"], | |
| "layer_norm_eps": 1e-06, | |
| "length_penalty": 1.0, | |
| "llm_hidden_size": 2048, | |
| "llm_vocab_size": 92553, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "min_length": 0, | |
| "mlp_bias": false, | |
| "model_type": "mmMamba_embedding", | |
| "no_repeat_ngram_size": 0, | |
| "norm_type": "rms_norm", | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "pixel_shuffle_loc": "pre", | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qk_normalization": true, | |
| "qkv_bias": false, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sep_token_id": null, | |
| "special_token_maps": {}, | |
| "suppress_tokens": null, | |
| "target_hidden_size": 2048, | |
| "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": "4.43.1", | |
| "typical_p": 1.0, | |
| "use_autoregressive_loss": false, | |
| "use_bfloat16": false, | |
| "use_flash_attn": true, | |
| "use_img_start_end_tokens": true, | |
| "use_ls": false, | |
| "use_pixel_shuffle_proj": true | |
| }, | |
| "force_image_size": 448, | |
| "llm_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "mmMambaForCausalLM" | |
| ], | |
| "attn_implementation": "flash_attention_2", | |
| "auto_map": { | |
| "AutoConfig": "configuration_mmMamba.mmMambaConfig", | |
| "AutoModel": "modeling_mmMamba.mmMambaForCausalLM", | |
| "AutoModelForCausalLM": "modeling_mmMamba.mmMambaForCausalLM" | |
| }, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bias": false, | |
| "bos_token_id": 1, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 2, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layers_block_type":[ | |
| "mha", "mamba2", "mamba2", "mamba2", "mha", "mamba2", "mamba2", "mamba2", | |
| "mha", "mamba2", "mamba2", "mamba2", "mha", "mamba2", "mamba2", "mamba2", | |
| "mha", "mamba2", "mamba2", "mamba2", "mha", "mamba2", "mamba2", "mamba2" | |
| ], | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "min_length": 0, | |
| "model_type": "mmMamba", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 2, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 1000000, | |
| "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": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "transformers_version": "4.43.1", | |
| "typical_p": 1.0, | |
| "use_bfloat16": true, | |
| "use_cache": false, | |
| "vocab_size": 92553, | |
| "feature_map": "softmax_dim", | |
| "feature_map_kwargs": { | |
| "eps": 1e-12, | |
| "fullspace": true | |
| }, | |
| "learned_kernel": "untied_head_einsum", | |
| "learned_kernel_kwargs":{ | |
| "feature_dim": 64, | |
| "skip_connection": false, | |
| "bias": false, | |
| "zero_init": false | |
| }, | |
| "tie_qk_kernels": false | |
| }, | |
| "max_dynamic_patch": 12, | |
| "min_dynamic_patch": 1, | |
| "model_type": "mmMamba_chat", | |
| "normalize_encoder_output": true, | |
| "pad2square": false, | |
| "ps_version": "v2", | |
| "select_layer": -1, | |
| "template": "internlm2-chat", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": null, | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_mlp": false, | |
| "use_thumbnail": true | |
| } |