| { |
| "_attn_implementation_autoset": false, |
| "add_cross_attention": false, |
| "architectures": [ |
| "DeepseekV3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "dtype": "bfloat16", |
| "eos_token_id": 1, |
| "ep_size": 1, |
| "finetuning_task": null, |
| "first_k_dense_replace": 3, |
| "head_dim": 16, |
| "hidden_act": "silu", |
| "hidden_size": 512, |
| "initializer_range": 0.02, |
| "intermediate_size": 256, |
| "is_decoder": false, |
| "kv_lora_rank": 32, |
| "max_position_embeddings": 163840, |
| "model_type": "deepseek_v3", |
| "moe_intermediate_size": 256, |
| "moe_layer_freq": 1, |
| "n_group": 1, |
| "n_routed_experts": 4, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 8, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 4, |
| "num_key_value_heads": 8, |
| "num_nextn_predict_layers": 0, |
| "pad_token_id": null, |
| "prefix": null, |
| "pretraining_tp": 1, |
| "pruned_heads": {}, |
| "q_lora_rank": 64, |
| "qk_head_dim": 48, |
| "qk_nope_head_dim": 32, |
| "qk_rope_head_dim": 16, |
| "rms_norm_eps": 1e-06, |
| "rope_interleave": true, |
| "rope_parameters": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 40.0, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 4096, |
| "rope_theta": 10000, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "routed_scaling_factor": 2.5, |
| "scoring_func": "sigmoid", |
| "sep_token_id": null, |
| "task_specific_params": null, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": null, |
| "topk_group": 1, |
| "topk_method": "noaux_tc", |
| "torchscript": false, |
| "transformers_version": "5.3.0", |
| "use_bfloat16": false, |
| "use_cache": true, |
| "v_head_dim": 32, |
| "vocab_size": 129280 |
| } |
|
|
