Update config.json

config.json

@@ -4,22 +4,19 @@
   ],
   "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,
   "bos_token_id": 163584,
-  "eos_token_id": 163586,
+  "dtype": "bfloat16",
+  "eos_token_id": 163585,
   "ep_size": 1,
   "first_k_dense_replace": 1,
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 11264,
   "kv_lora_rank": 512,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 131072,
   "model_type": "deepseek_v3",
   "moe_intermediate_size": 1408,
   "moe_layer_freq": 1,
@@ -31,22 +28,27 @@
   "num_experts_per_tok": 6,
   "num_hidden_layers": 27,
   "num_key_value_heads": 16,
-  "num_nextn_predict_layers": 0,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 163839,
   "pretraining_tp": 1,
   "q_lora_rank": null,
+  "qk_head_dim": 192,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 50000.0,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 800000.0,
+    "rope_type": "default"
+  },
   "routed_scaling_factor": 2.446,
   "scoring_func": "sigmoid",
   "seq_aux": true,
   "tie_word_embeddings": false,
   "topk_group": 1,
   "topk_method": "noaux_tc",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
-  "use_cache": true,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
   "v_head_dim": 128,
   "vocab_size": 163840
-}
+}