OpenMoE base pytorch checkpoint

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "OpenMoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "dropout_rate": 0.0,
+  "enable_comm_overlap": false,
+  "enable_hierarchical_alltoall": false,
+  "enable_kernel": false,
+  "enable_load_balance": false,
+  "eos_token_id": 2,
+  "expert_parallel": null,
+  "head_dim": 64,
+  "hidden_act": "swiglu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_epsilon": 1e-06,
+  "load_balance_beam_width": 8,
+  "load_balance_group_swap_factor": 0.4,
+  "load_balance_tolerance": 0.1,
+  "max_position_embeddings": 2048,
+  "mlp_gated": true,
+  "model_type": "llama",
+  "moe_layer_interval": 4,
+  "num_attention_heads": 12,
+  "num_experts": 16,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_capacity_factor_eval": 2.0,
+  "router_capacity_factor_train": 1.25,
+  "router_drop_tks": true,
+  "router_min_capacity": 4,
+  "router_noisy_policy": null,
+  "router_topk": 2,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 256384
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bd7394ac65e876a8f6887615d2af7628d226bead374fa670eec1494fb081b3
+size 3198692805