Upload DogeForCausalLM

config.json

@@ -1,43 +1,34 @@
 {
-  "_name_or_path": "SmallDoge/Doge-20M",
   "architectures": [
     "DogeForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_doge.DogeConfig",
-    "AutoModelForCausalLM": "modeling_doge.DogeForCausalLM"
-  },
-  "bos_token_id": 0,
-  "dynamic_mask_ratio": 0.0,
-  "eos_token_id": 1,
-  "expert_retrieval_size": 256,
   "hidden_act": "silu",
-  "hidden_bias": false,
   "hidden_dropout": 0.0,
   "hidden_size": 256,
   "initializer_range": 0.02,
   "intermediate_size": 512,
   "is_moe": false,
+  "keep_window_size": 2048,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "doge",
+  "norm_topk_prob": false,
   "num_attention_heads": 2,
-  "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": 8,
   "num_key_value_heads": 1,
-  "pad_token_id": 2,
+  "output_router_logits": false,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "factor": 4.0,
-    "original_max_position_embeddings": 2048,
-    "rope_type": "dynamic"
-  },
+  "rope_scaling": null,
   "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.53.0.dev0",
   "use_cache": true,
   "vocab_size": 32768
 }

generation_config.json

@@ -1,7 +1,4 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 2,
-  "transformers_version": "4.48.3"
-}
+{
+  "_from_model_config": true,
+  "transformers_version": "4.53.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3632a5c94bc7d3cf66602318b168603ec19f1025e0aef01c286d65e30ed55e8b
-size 52482152
+oid sha256:ac54b1befcb0193baa997e2434b58498a5a2f4c3f282b33e82ba748cb8030a8c
+size 52487888