| { |
| "architectures": [ |
| "InternVLChatModel" |
| ], |
| "downsample_ratio": 0.5, |
| "dynamic_image_size": true, |
| "force_image_size": 448, |
| "llm_config": { |
| "_name_or_path": "KISTI-KONI/KONI-4B-instruct-20250901", |
| "_sliding_window_pattern": 6, |
| "architectures": [ |
| "Gemma3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": null, |
| "boi_token_index": 255999, |
| "bos_token_id": 2, |
| "cache_implementation": "hybrid", |
| "eoi_token_index": 256000, |
| "eos_token_id": 1, |
| "final_logit_softcapping": null, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 2560, |
| "image_token_index": 262144, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "max_position_embeddings": 131072, |
| "mm_tokens_per_image": 256, |
| "model_type": "gemma3", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 34, |
| "num_key_value_heads": 4, |
| "pad_token_id": 0, |
| "query_pre_attn_scalar": 256, |
| "rms_norm_eps": 1e-06, |
| "rope_local_base_freq": 10000.0, |
| "rope_scaling": { |
| "factor": 8.0, |
| "rope_type": "linear" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": 1024, |
| "text_config": { |
| "_name_or_path": "", |
| "_sliding_window_pattern": 6, |
| "add_cross_attention": false, |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 2, |
| "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": 1, |
| "exponential_decay_length_penalty": null, |
| "final_logit_softcapping": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 2304, |
| "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 |
| }, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 131072, |
| "min_length": 0, |
| "model_type": "gemma3_text", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 8, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 26, |
| "num_key_value_heads": 4, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 0, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "query_pre_attn_scalar": 256, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_local_base_freq": 10000.0, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sep_token_id": null, |
| "sliding_window": 4096, |
| "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, |
| "use_cache": true, |
| "vocab_size": 262208 |
| }, |
| "torch_dtype": "bfloat16", |
| "use_cache": false, |
| "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, |
| "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_pytorch_tanh", |
| "hidden_size": 768, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": 224, |
| "intermediate_size": 3072, |
| "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": "siglip_vision_model", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 12, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_channels": 3, |
| "num_hidden_layers": 12, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "patch_size": 16, |
| "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, |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| }, |
| "vocab_size": 262152 |
| }, |
| "max_dynamic_patch": 12, |
| "min_dynamic_patch": 1, |
| "model_type": "internvl_chat", |
| "output_attentions": false, |
| "pad2square": false, |
| "ps_version": "v2", |
| "select_layer": -1, |
| "template": "gemma3", |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers_version": null, |
| "use_backbone_lora": 0, |
| "use_llm_lora": 0, |
| "use_thumbnail": true, |
| "vision_config": { |
| "architectures": [ |
| "InternVisionModel" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", |
| "AutoModel": "modeling_intern_vit.InternVisionModel" |
| }, |
| "drop_path_rate": 0.0, |
| "dropout": 0.0, |
| "hidden_act": "gelu", |
| "hidden_size": 1024, |
| "image_size": 448, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-06, |
| "model_type": "intern_vit_6b", |
| "norm_type": "layer_norm", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "patch_size": 14, |
| "qk_normalization": false, |
| "qkv_bias": true, |
| "torch_dtype": "bfloat16", |
| "use_flash_attn": true |
| } |
| } |
|
|
