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
+}

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": "5.5.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2be05f0947b809cc2de317e158cf2764844d62f707856f4fb34db9131eecf71
+size 2519929824

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ea59a87b004653cf32b962eab21e3e64e3697e9b34177a9453d247697cf6ad
+size 1262848364

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d895ccae2b55d4ea213653ca4a80d00de131463e105716eab1b7022906f260bf
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e81a0b2afa59686ef1860543e0c430e9f2158cb60d3f799023a1619c5009270
+size 10233

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739c5713bb5758511b2bae79be46c940db56a861c1c0174f91add6f7de16f6bf
+size 5713