{ "architectures": [ "KananaVForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration.KananaVConfig", "AutoModelForVision2Seq": "modeling.KananaVForConditionalGeneration", "AutoImageProcessor": "processing_image.KananaVImageProcessor", "AutoProcessor": "processing.KananaVProcessor" }, "model_type": "kanana-1.5-v", "plora_config": null, "projector_config": { "_attn_implementation_autoset": false, "add_cross_attention": false, "architectures": null, "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, "depth": 2, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_hidden_size": 1280, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "feature_layer_index": -1, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "merge_size": 2, "min_length": 0, "mlp_depth": 2, "model_type": "kanana-1.5-v-visual_projector", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_eos_tokens": 0, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 2048, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "pos_emb": true, "pos_emb_size": 576, "prefix": null, "prenorm": false, "problem_type": null, "projector_type": "dynamic-c-abs", "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, "typical_p": 1.0, "use_bfloat16": false }, "text_config": { "_name_or_path": "kakaocorp/kanana-1.5-3b-instruct", "_attn_implementation_autoset": false, "add_cross_attention": false, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 128000, "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": 128009, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 9216, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "min_length": 0, "mlp_bias": false, "model_type": "kanana-1.5-3b-instruct", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 128001, "prefix": null, "pretraining_tp": 1, "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": null, "rope_theta": 8000000.0, "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, "typical_p": 1.0, "use_bfloat16": false, "use_cache": false, "vocab_size": 128259 }, "torch_dtype": "bfloat16", "transformers_version": "4.51.3", "vision_config": { "_attn_implementation_autoset": false, "add_cross_attention": false, "architectures": null, "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, "depth": 32, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "embed_dim": 1280, "encoder_no_repeat_ngram_size": 0, "encoder_type": "qwen2-vl-ve", "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "quick_gelu", "hidden_size": 1280, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_mean": [ 0.48145466, 0.4578275, 0.40821073 ], "image_size": "dynamic", "image_std": [ 0.26862954, 0.26130258, 0.27577711 ], "in_channels": 3, "in_chans": 3, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "mlp_ratio": 4, "model_type": "kanana-1.5-v-visual-encoder", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_heads": 16, "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, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "spatial_merge_size": 2, "spatial_patch_size": 14, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "temporal_patch_size": 2, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false } }