{ "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": false, "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, "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": "", "transformers_version": "4.56.1", "head_dim": 128, "max_window_layers": 48, "model_type": "rnd1", "is_causal": false, "tf_legacy_loss": false, "use_bfloat16": false, "moe_backend": "hf", "num_diffusion_steps": 256, "mask_token_id": 151669, "output_attentions": false, "auto_map": { "AutoConfig": "configuration_rnd.RND1Config", "AutoModel": "modeling_rnd.RND1Model", "AutoModelForMaskedLM": "modeling_rnd.RND1LM" } }