| { |
| "add_cross_attention": false, |
| "architectures": [ |
| "InternVLForConditionalGeneration" |
| ], |
| "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, |
| "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, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_seq_length": 256, |
| "image_token_id": 151671, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "internvl", |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "prefix": null, |
| "problem_type": null, |
| "projector_hidden_act": "gelu", |
| "pruned_heads": {}, |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "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, |
| "text_config": { |
| "vocab_size": 151936, |
| "max_position_embeddings": 40960, |
| "hidden_size": 2048, |
| "intermediate_size": 6144, |
| "num_hidden_layers": 48, |
| "num_attention_heads": 32, |
| "use_sliding_window": false, |
| "sliding_window": null, |
| "num_key_value_heads": 4, |
| "hidden_act": "silu", |
| "initializer_range": 0.02, |
| "rms_norm_eps": 1e-06, |
| "use_cache": true, |
| "rope_theta": 1000000.0, |
| "rope_scaling": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "decoder_sparse_step": 1, |
| "moe_intermediate_size": 768, |
| "num_experts_per_tok": 8, |
| "num_experts": 128, |
| "norm_topk_prob": true, |
| "output_router_logits": false, |
| "router_aux_loss_coef": 0.001, |
| "mlp_only_layers": [], |
| "return_dict": true, |
| "output_hidden_states": false, |
| "torchscript": false, |
| "torch_dtype": "bfloat16", |
| "pruned_heads": {}, |
| "tie_word_embeddings": false, |
| "chunk_size_feed_forward": 0, |
| "is_encoder_decoder": false, |
| "is_decoder": false, |
| "cross_attention_hidden_size": null, |
| "add_cross_attention": false, |
| "tie_encoder_decoder": false, |
| "architectures": [ |
| "Qwen3MoeForCausalLM" |
| ], |
| "finetuning_task": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "task_specific_params": null, |
| "problem_type": null, |
| "tokenizer_class": null, |
| "prefix": null, |
| "bos_token_id": 151643, |
| "pad_token_id": null, |
| "eos_token_id": 151645, |
| "sep_token_id": null, |
| "decoder_start_token_id": null, |
| "max_length": 20, |
| "min_length": 0, |
| "do_sample": false, |
| "early_stopping": false, |
| "num_beams": 1, |
| "num_beam_groups": 1, |
| "diversity_penalty": 0.0, |
| "temperature": 1.0, |
| "top_k": 50, |
| "top_p": 1.0, |
| "typical_p": 1.0, |
| "repetition_penalty": 1.0, |
| "length_penalty": 1.0, |
| "no_repeat_ngram_size": 0, |
| "encoder_no_repeat_ngram_size": 0, |
| "bad_words_ids": null, |
| "num_return_sequences": 1, |
| "output_scores": false, |
| "return_dict_in_generate": false, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "remove_invalid_values": false, |
| "exponential_decay_length_penalty": null, |
| "suppress_tokens": null, |
| "begin_suppress_tokens": null, |
| "_name_or_path": "/root/codespace/checkpoints/Qwen3-30B-A3B", |
| "head_dim": 128, |
| "max_window_layers": 48, |
| "model_type": "qwen3_moe", |
| "tf_legacy_loss": false, |
| "use_bfloat16": false, |
| "output_attentions": false |
| }, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "transformers_version": "4.54.0", |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "vision_config": { |
| "return_dict": true, |
| "output_hidden_states": false, |
| "torchscript": false, |
| "torch_dtype": "bfloat16", |
| "pruned_heads": {}, |
| "tie_word_embeddings": true, |
| "chunk_size_feed_forward": 0, |
| "is_encoder_decoder": false, |
| "is_decoder": false, |
| "cross_attention_hidden_size": null, |
| "add_cross_attention": false, |
| "tie_encoder_decoder": false, |
| "architectures": [ |
| "InternVisionModel" |
| ], |
| "finetuning_task": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "task_specific_params": null, |
| "problem_type": null, |
| "tokenizer_class": null, |
| "prefix": null, |
| "bos_token_id": null, |
| "pad_token_id": null, |
| "eos_token_id": null, |
| "sep_token_id": null, |
| "decoder_start_token_id": null, |
| "max_length": 20, |
| "min_length": 0, |
| "do_sample": false, |
| "early_stopping": false, |
| "num_beams": 1, |
| "num_beam_groups": 1, |
| "diversity_penalty": 0.0, |
| "temperature": 1.0, |
| "top_k": 50, |
| "top_p": 1.0, |
| "typical_p": 1.0, |
| "repetition_penalty": 1.0, |
| "length_penalty": 1.0, |
| "no_repeat_ngram_size": 0, |
| "encoder_no_repeat_ngram_size": 0, |
| "bad_words_ids": null, |
| "num_return_sequences": 1, |
| "output_scores": false, |
| "return_dict_in_generate": false, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "remove_invalid_values": false, |
| "exponential_decay_length_penalty": null, |
| "suppress_tokens": null, |
| "begin_suppress_tokens": null, |
| "_name_or_path": "", |
| "dropout": 0.0, |
| "initializer_factor": 0.1, |
| "model_type": "internvl_vision", |
| "tf_legacy_loss": false, |
| "use_bfloat16": false, |
| "hidden_size": 1024, |
| "num_hidden_layers": 24, |
| "num_attention_heads": 16, |
| "attention_bias": true, |
| "use_qk_norm": false, |
| "intermediate_size": 4096, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "attention_dropout": 0.0, |
| "projection_dropout": 0.0, |
| "initializer_range": 1e-10, |
| "norm_type": "layer_norm", |
| "layer_norm_eps": 1e-06, |
| "image_size": [ |
| 448, |
| 448 |
| ], |
| "patch_size": [ |
| 14, |
| 14 |
| ], |
| "num_channels": 3, |
| "use_mask_token": false, |
| "use_absolute_position_embeddings": true, |
| "layer_scale_init_value": 0.1, |
| "use_mean_pooling": true, |
| "output_attentions": false |
| }, |
| "vision_feature_layer": -1, |
| "vision_feature_select_strategy": "default" |
| } |
