初始化项目，由ModelHub XC社区提供模型

Model: Ba2han/TR_SFT
Source: Original Platform

last-checkpoint/config.json

@@ -0,0 +1,79 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1664,
+  "initializer_range": 0.02,
+  "intermediate_size": 4160,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 16384,
+  "max_window_layers": 42,
+  "model_name": "TR_CPT1/checkpoint-10000",
+  "model_type": "qwen3",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-08,
+  "rope_parameters": {
+    "rope_theta": 500000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "unsloth_version": "2026.7.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 60800
+}