初始化项目，由ModelHub XC社区提供模型

Model: kshitijthakkar/loggenix-moe-0.3B-A0.1B-e3-lr7e5-b16-4090
Source: Original Platform

checkpoints/epoch_1_step_10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f569536d19906978c19e8da5f3ffe0306a7a17ddfa3b831636cec1b334511623
+size 629414451

checkpoints/epoch_1_step_280000/config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.1,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 12,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 512,
+  "norm_topk_prob": true,
+  "num_attention_heads": 8,
+  "num_experts": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "output_router_logits": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoints/epoch_1_step_280000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15387ebf9655ffc1d92c79d1980e7ded19fed72bf0c135a179374bf00dc121cd
+size 629432563

checkpoints/epoch_1_step_50/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399e2e271f6b14818ac96127c556675b978a4fdfd7f3a4b4b192932eb4e1b841
+size 629414034

checkpoints/epoch_1_step_500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03ef4926b0ec6f33895ed1805bedae3193791b3ad02e2737fb911beddf8b456
+size 629414034