Upload config.json with huggingface_hub

config.json

@@ -0,0 +1,62 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "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": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.0125,
+  "intermediate_size": 10944,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 8192,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1024,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "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": 1.0,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}