Upload folder using huggingface_hub

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "Qwen3MoEForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "decoder_sparse_step": 1,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "eagle_config": {
+    "eagle_aux_hidden_state_layer_ids": [
+      1,
+      15,
+      28
+    ]
+  },
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "max_window_layers": 1,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 1792,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.1,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 128256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4e8ba2b96ab2b5d344f579ee94f00412366d81bfb1429d000623348afb0652
+size 3316540960

training_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97dc51ccc81b09143a72d5f0f4027c0d0f21ec4e9cb7ca9115acaa34e1f73a8
+size 4311