| { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "DeepseekV3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_deepseek.DeepseekV3Config", | |
| "AutoModel": "modeling_deepseek.DeepseekV3Model", | |
| "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM" | |
| }, | |
| "aux_loss_alpha": 0.001, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 163584, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0, | |
| "do_sample": false, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 163585, | |
| "ep_size": 1, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "first_k_dense_replace": 1, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18432, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "kv_lora_rank": 512, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1, | |
| "max_length": 20, | |
| "max_position_embeddings": 262144, | |
| "min_length": 0, | |
| "model_type": "deepseek_v3", | |
| "moe_intermediate_size": 2048, | |
| "moe_layer_freq": 1, | |
| "n_group": 1, | |
| "n_routed_experts": 384, | |
| "n_shared_experts": 1, | |
| "no_repeat_ngram_size": 0, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 64, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 61, | |
| "num_key_value_heads": 64, | |
| "num_nextn_predict_layers": 0, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 163839, | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "q_lora_rank": 1536, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "dynamic": false, | |
| "num_bits": 4, | |
| "type": "float", | |
| "group_size": 16 | |
| }, | |
| "weights": { | |
| "dynamic": false, | |
| "num_bits": 4, | |
| "type": "float", | |
| "group_size": 16 | |
| }, | |
| "targets": [ | |
| "Linear" | |
| ] | |
| } | |
| }, | |
| "ignore": [ | |
| "lm_head", | |
| "model.layers.0.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.0.self_attn.kv_b_proj", | |
| "model.layers.0.self_attn.q_a_proj", | |
| "model.layers.0.self_attn.q_b_proj", | |
| "model.layers.1.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.1.self_attn.kv_b_proj", | |
| "model.layers.1.self_attn.q_a_proj", | |
| "model.layers.1.self_attn.q_b_proj", | |
| "model.layers.10.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.10.self_attn.kv_b_proj", | |
| "model.layers.10.self_attn.q_a_proj", | |
| "model.layers.10.self_attn.q_b_proj", | |
| "model.layers.11.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.11.self_attn.kv_b_proj", | |
| "model.layers.11.self_attn.q_a_proj", | |
| "model.layers.11.self_attn.q_b_proj", | |
| "model.layers.12.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.12.self_attn.kv_b_proj", | |
| "model.layers.12.self_attn.q_a_proj", | |
| "model.layers.12.self_attn.q_b_proj", | |
| "model.layers.13.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.13.self_attn.kv_b_proj", | |
| "model.layers.13.self_attn.q_a_proj", | |
| "model.layers.13.self_attn.q_b_proj", | |
| "model.layers.14.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.14.self_attn.kv_b_proj", | |
| "model.layers.14.self_attn.q_a_proj", | |
| "model.layers.14.self_attn.q_b_proj", | |
| "model.layers.15.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.15.self_attn.kv_b_proj", | |
| "model.layers.15.self_attn.q_a_proj", | |
| "model.layers.15.self_attn.q_b_proj", | |
| "model.layers.16.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.16.self_attn.kv_b_proj", | |
| "model.layers.16.self_attn.q_a_proj", | |
| "model.layers.16.self_attn.q_b_proj", | |
| "model.layers.17.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.17.self_attn.kv_b_proj", | |
| "model.layers.17.self_attn.q_a_proj", | |
| "model.layers.17.self_attn.q_b_proj", | |
| "model.layers.18.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.18.self_attn.kv_b_proj", | |
| "model.layers.18.self_attn.q_a_proj", | |
| "model.layers.18.self_attn.q_b_proj", | |
| "model.layers.19.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.19.self_attn.kv_b_proj", | |
| "model.layers.19.self_attn.q_a_proj", | |
| "model.layers.19.self_attn.q_b_proj", | |
| "model.layers.2.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.2.self_attn.kv_b_proj", | |
| "model.layers.2.self_attn.q_a_proj", | |
| "model.layers.2.self_attn.q_b_proj", | |
| "model.layers.20.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.20.self_attn.kv_b_proj", | |
| "model.layers.20.self_attn.q_a_proj", | |
| "model.layers.20.self_attn.q_b_proj", | |
| "model.layers.21.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.21.self_attn.kv_b_proj", | |
| "model.layers.21.self_attn.q_a_proj", | |
| "model.layers.21.self_attn.q_b_proj", | |
| "model.layers.22.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.22.self_attn.kv_b_proj", | |
| "model.layers.22.self_attn.q_a_proj", | |
| "model.layers.22.self_attn.q_b_proj", | |
| "model.layers.23.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.23.self_attn.kv_b_proj", | |
| "model.layers.23.self_attn.q_a_proj", | |
| "model.layers.23.self_attn.q_b_proj", | |
| "model.layers.24.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.24.self_attn.kv_b_proj", | |
| "model.layers.24.self_attn.q_a_proj", | |
| "model.layers.24.self_attn.q_b_proj", | |
| "model.layers.25.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.25.self_attn.kv_b_proj", | |
| "model.layers.25.self_attn.q_a_proj", | |
| "model.layers.25.self_attn.q_b_proj", | |
| "model.layers.26.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.26.self_attn.kv_b_proj", | |
| "model.layers.26.self_attn.q_a_proj", | |
| "model.layers.26.self_attn.q_b_proj", | |
| "model.layers.27.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.27.self_attn.kv_b_proj", | |
| "model.layers.27.self_attn.q_a_proj", | |
| "model.layers.27.self_attn.q_b_proj", | |
| "model.layers.28.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.28.self_attn.kv_b_proj", | |
| "model.layers.28.self_attn.q_a_proj", | |
| "model.layers.28.self_attn.q_b_proj", | |
| "model.layers.29.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.29.self_attn.kv_b_proj", | |
| "model.layers.29.self_attn.q_a_proj", | |
| "model.layers.29.self_attn.q_b_proj", | |
| "model.layers.3.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.3.self_attn.kv_b_proj", | |
| "model.layers.3.self_attn.q_a_proj", | |
| "model.layers.3.self_attn.q_b_proj", | |
| "model.layers.30.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.30.self_attn.kv_b_proj", | |
| "model.layers.30.self_attn.q_a_proj", | |
| "model.layers.30.self_attn.q_b_proj", | |
| "model.layers.31.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.31.self_attn.kv_b_proj", | |
| "model.layers.31.self_attn.q_a_proj", | |
| "model.layers.31.self_attn.q_b_proj", | |
| "model.layers.32.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.32.self_attn.kv_b_proj", | |
| "model.layers.32.self_attn.q_a_proj", | |
| "model.layers.32.self_attn.q_b_proj", | |
| "model.layers.33.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.33.self_attn.kv_b_proj", | |
| "model.layers.33.self_attn.q_a_proj", | |
| "model.layers.33.self_attn.q_b_proj", | |
| "model.layers.34.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.34.self_attn.kv_b_proj", | |
| "model.layers.34.self_attn.q_a_proj", | |
| "model.layers.34.self_attn.q_b_proj", | |
| "model.layers.35.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.35.self_attn.kv_b_proj", | |
| "model.layers.35.self_attn.q_a_proj", | |
| "model.layers.35.self_attn.q_b_proj", | |
| "model.layers.36.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.36.self_attn.kv_b_proj", | |
| "model.layers.36.self_attn.q_a_proj", | |
| "model.layers.36.self_attn.q_b_proj", | |
| "model.layers.37.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.37.self_attn.kv_b_proj", | |
| "model.layers.37.self_attn.q_a_proj", | |
| "model.layers.37.self_attn.q_b_proj", | |
| "model.layers.38.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.38.self_attn.kv_b_proj", | |
| "model.layers.38.self_attn.q_a_proj", | |
| "model.layers.38.self_attn.q_b_proj", | |
| "model.layers.39.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.39.self_attn.kv_b_proj", | |
| "model.layers.39.self_attn.q_a_proj", | |
| "model.layers.39.self_attn.q_b_proj", | |
| "model.layers.4.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.4.self_attn.kv_b_proj", | |
| "model.layers.4.self_attn.q_a_proj", | |
| "model.layers.4.self_attn.q_b_proj", | |
| "model.layers.40.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.40.self_attn.kv_b_proj", | |
| "model.layers.40.self_attn.q_a_proj", | |
| "model.layers.40.self_attn.q_b_proj", | |
| "model.layers.41.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.41.self_attn.kv_b_proj", | |
| "model.layers.41.self_attn.q_a_proj", | |
| "model.layers.41.self_attn.q_b_proj", | |
| "model.layers.42.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.42.self_attn.kv_b_proj", | |
| "model.layers.42.self_attn.q_a_proj", | |
| "model.layers.42.self_attn.q_b_proj", | |
| "model.layers.43.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.43.self_attn.kv_b_proj", | |
| "model.layers.43.self_attn.q_a_proj", | |
| "model.layers.43.self_attn.q_b_proj", | |
| "model.layers.44.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.44.self_attn.kv_b_proj", | |
| "model.layers.44.self_attn.q_a_proj", | |
| "model.layers.44.self_attn.q_b_proj", | |
| "model.layers.45.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.45.self_attn.kv_b_proj", | |
| "model.layers.45.self_attn.q_a_proj", | |
| "model.layers.45.self_attn.q_b_proj", | |
| "model.layers.46.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.46.self_attn.kv_b_proj", | |
| "model.layers.46.self_attn.q_a_proj", | |
| "model.layers.46.self_attn.q_b_proj", | |
| "model.layers.47.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.47.self_attn.kv_b_proj", | |
| "model.layers.47.self_attn.q_a_proj", | |
| "model.layers.47.self_attn.q_b_proj", | |
| "model.layers.48.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.48.self_attn.kv_b_proj", | |
| "model.layers.48.self_attn.q_a_proj", | |
| "model.layers.48.self_attn.q_b_proj", | |
| "model.layers.49.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.49.self_attn.kv_b_proj", | |
| "model.layers.49.self_attn.q_a_proj", | |
| "model.layers.49.self_attn.q_b_proj", | |
| "model.layers.5.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.5.self_attn.kv_b_proj", | |
| "model.layers.5.self_attn.q_a_proj", | |
| "model.layers.5.self_attn.q_b_proj", | |
| "model.layers.50.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.50.self_attn.kv_b_proj", | |
| "model.layers.50.self_attn.q_a_proj", | |
| "model.layers.50.self_attn.q_b_proj", | |
| "model.layers.51.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.51.self_attn.kv_b_proj", | |
| "model.layers.51.self_attn.q_a_proj", | |
| "model.layers.51.self_attn.q_b_proj", | |
| "model.layers.52.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.52.self_attn.kv_b_proj", | |
| "model.layers.52.self_attn.q_a_proj", | |
| "model.layers.52.self_attn.q_b_proj", | |
| "model.layers.53.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.53.self_attn.kv_b_proj", | |
| "model.layers.53.self_attn.q_a_proj", | |
| "model.layers.53.self_attn.q_b_proj", | |
| "model.layers.54.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.54.self_attn.kv_b_proj", | |
| "model.layers.54.self_attn.q_a_proj", | |
| "model.layers.54.self_attn.q_b_proj", | |
| "model.layers.55.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.55.self_attn.kv_b_proj", | |
| "model.layers.55.self_attn.q_a_proj", | |
| "model.layers.55.self_attn.q_b_proj", | |
| "model.layers.56.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.56.self_attn.kv_b_proj", | |
| "model.layers.56.self_attn.q_a_proj", | |
| "model.layers.56.self_attn.q_b_proj", | |
| "model.layers.57.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.57.self_attn.kv_b_proj", | |
| "model.layers.57.self_attn.q_a_proj", | |
| "model.layers.57.self_attn.q_b_proj", | |
| "model.layers.58.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.58.self_attn.kv_b_proj", | |
| "model.layers.58.self_attn.q_a_proj", | |
| "model.layers.58.self_attn.q_b_proj", | |
| "model.layers.59.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.59.self_attn.kv_b_proj", | |
| "model.layers.59.self_attn.q_a_proj", | |
| "model.layers.59.self_attn.q_b_proj", | |
| "model.layers.6.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.6.self_attn.kv_b_proj", | |
| "model.layers.6.self_attn.q_a_proj", | |
| "model.layers.6.self_attn.q_b_proj", | |
| "model.layers.60.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.60.self_attn.kv_b_proj", | |
| "model.layers.60.self_attn.q_a_proj", | |
| "model.layers.60.self_attn.q_b_proj", | |
| "model.layers.7.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.7.self_attn.kv_b_proj", | |
| "model.layers.7.self_attn.q_a_proj", | |
| "model.layers.7.self_attn.q_b_proj", | |
| "model.layers.8.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.8.self_attn.kv_b_proj", | |
| "model.layers.8.self_attn.q_a_proj", | |
| "model.layers.8.self_attn.q_b_proj", | |
| "model.layers.9.self_attn.kv_a_proj_with_mqa", | |
| "model.layers.9.self_attn.kv_b_proj", | |
| "model.layers.9.self_attn.q_a_proj", | |
| "model.layers.9.self_attn.q_b_proj", | |
| "mm_projector*", | |
| "vision_tower*" | |
| ], | |
| "quant_algo": "NVFP4", | |
| "kv_cache_scheme": { | |
| "dynamic": false, | |
| "num_bits": 8, | |
| "type": "float" | |
| }, | |
| "producer": { | |
| "name": "modelopt", | |
| "version": "0.41.0rc2.dev54+g99912fbdf" | |
| }, | |
| "quant_method": "modelopt" | |
| }, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 0.00001, | |
| "rope_scaling": { | |
| "beta_fast": 32, | |
| "beta_slow": 1, | |
| "factor": 64, | |
| "mscale": 1, | |
| "mscale_all_dim": 1, | |
| "original_max_position_embeddings": 4096, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 50000, | |
| "routed_scaling_factor": 2.827, | |
| "scoring_func": "sigmoid", | |
| "sep_token_id": null, | |
| "seq_aux": true, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1, | |
| "topk_group": 1, | |
| "topk_method": "noaux_tc", | |
| "torchscript": false, | |
| "transformers_version": "4.56.2", | |
| "typical_p": 1, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "v_head_dim": 128, | |
| "vocab_size": 163840 | |
| } | |