Upload DogeForCausalLM

config.json

@@ -11,27 +11,27 @@
   "bos_token_id": 0,
   "dynamic_mask_ratio": 0.0,
   "eos_token_id": 1,
-  "expert_retrieval_size": 64,
+  "expert_retrieval_size": 256,
   "hidden_act": "silu",
   "hidden_bias": false,
   "hidden_dropout": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "intermediate_size": 1024,
   "is_moe": false,
   "keep_window_size": 2048,
   "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "doge",
   "norm_topk_prob": false,
-  "num_attention_heads": 6,
+  "num_attention_heads": 4,
   "num_cdmoe_experts": 16348,
   "num_cdmoe_experts_per_head": 8,
   "num_cdmoe_heads": 4,
   "num_experts": 16384,
   "num_experts_per_tok": 64,
-  "num_hidden_layers": 24,
-  "num_key_value_heads": 3,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 2,
   "output_router_logits": false,
   "pad_token_id": 2,
   "rms_norm_eps": 1e-06,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ce781a449231f7744179cffa570d5f4e727f7867476b6810b9e8c8c5e80530
-size 305429944
+oid sha256:0c0974eb9bdd4c39eb840024424b9ca67186461d7ad8a7b414289cedd3f2289d
+size 109174080