初始化项目，由ModelHub XC社区提供模型

Model: Ba2han/qwen-test-3-longer
Source: Original Platform

last-checkpoint/config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50030,
+  "dtype": "bfloat16",
+  "eos_token_id": 50031,
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "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": 8192,
+  "max_window_layers": 40,
+  "model_name": "Ba2han/qwen-test-3",
+  "model_type": "qwen3",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 50034,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "unsloth_version": "2026.3.7",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 50048
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50030,
+  "eos_token_id": [
+    50031
+  ],
+  "max_length": 8192,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 50034,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6569991fe5914edcf1c96260a63c3ff12b7fa3cd2266c283296c51800fa69db
+size 1310251320

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5048ccbf797ffd61df0dfb9d8f33476e1e0efb483ce46d517d45c6750a3bed
+size 1541205579

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6d8fafcd1ee268414be5acf0366296af5b03d60871978712eac1979cb42d65
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff34282066e810d250dfa7f90fc209163224334619707e0fa00f47f9d30049a7
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f2c26c5a6dc92a2a72879d1410c36faaee7264339e7985a308074e41dc4990
+size 5713