config.json

{
  "_attn_implementation_autoset": false,
  "_name_or_path": "./sglang/r1_base/",
  "add_cross_attention": false,
  "architectures": [
    "DeepseekV3ForCausalLMNextN"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "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": 0,
  "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,
  "ep_size": 1,
  "exponential_decay_length_penalty": null,
  "finetuning_task": null,
  "first_k_dense_replace": 3,
  "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": 1.0,
  "max_length": 20,
  "max_position_embeddings": 163840,
  "min_length": 0,
  "model_type": "deepseek_v3",
  "moe_intermediate_size": 2048,
  "moe_layer_freq": 1,
  "n_group": 8,
  "n_routed_experts": 256,
  "n_shared_experts": 1,
  "no_repeat_ngram_size": 0,
  "norm_topk_prob": true,
  "num_attention_heads": 128,
  "num_beam_groups": 1,
  "num_beams": 1,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 1,
  "num_key_value_heads": 128,
  "num_nextn_predict_layers": 1,
  "num_return_sequences": 1,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_scores": false,
  "pad_token_id": null,
  "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": {
    "activation_scheme": "dynamic",
    "fmt": "e4m3",
    "quant_method": "fp8",
    "weight_block_size": [
      128,
      128
    ]
  },
  "remove_invalid_values": false,
  "repetition_penalty": 1.0,
  "return_dict": true,
  "return_dict_in_generate": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 40,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 4096,
    "type": "yarn"
  },
  "rope_theta": 10000,
  "routed_scaling_factor": 2.5,
  "scoring_func": "sigmoid",
  "sep_token_id": null,
  "seq_aux": true,
  "suppress_tokens": null,
  "task_specific_params": null,
  "temperature": 1.0,
  "tf_legacy_loss": false,
  "tie_encoder_decoder": false,
  "tie_word_embeddings": false,
  "tokenizer_class": null,
  "top_k": 50,
  "top_p": 1.0,
  "topk_group": 4,
  "topk_method": "noaux_tc",
  "torch_dtype": "bfloat16",
  "torchscript": false,
  "transformers_version": "4.48.3",
  "typical_p": 1.0,
  "use_bfloat16": false,
  "use_cache": true,
  "v_head_dim": 128,
  "vocab_size": 129280
}