初始化项目，由ModelHub XC社区提供模型

Model: Ba2han/test_CPTl
Source: Original Platform

last-checkpoint/config.json

@@ -0,0 +1,77 @@
+{
+  "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": 1792,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "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"
+  ],
+  "max_position_embeddings": 16384,
+  "max_window_layers": 40,
+  "model_name": "Ba2han/TR_CPTs",
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 40,
+  "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": "5.8.0",
+  "unsloth_version": "2026.7.5",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 60800
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    3
+  ],
+  "max_length": 16384,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.8.0",
+  "use_cache": false
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c3e22ed454cecef7c3ff96df36f50c43f63fcd3f166257afc270934206d243
+size 2934389864

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606c4e839c35b79593f5d30752dd36400099bb4ac6b729a22b22111e12133052
+size 1469364408

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27978b0c0a2d70a6d9e24fba0f2ed928bba9b47aecb6cc92523c33dd4a9bc29f
+size 14917

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4883ea9e9e4170ef036b08f27772e01a500be9d13e3c9492d90b6357d7e8c6
+size 14917

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e953206a3177f2c18733523d3423abb646dbbf7cc9830b1eed182b0c5c01d7
+size 9785

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2957cfba202003d4b899dc4e984a3a927a9d2cbc96175de28f40afa81dd93c
+size 5841