初始化项目，由ModelHub XC社区提供模型

Model: build-small-hackathon/Nemotron-nano-4b-escape-room
Source: Original Platform

config.json

@@ -0,0 +1,61 @@
+{
+    "architectures": [
+        "NemotronHForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_head_dim": 128,
+    "auto_map": {
+        "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
+        "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
+    },
+    "bos_token_id": 1,
+    "chunk_size": 256,
+    "conv_kernel": 4,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 11,
+    "expand": 2,
+    "head_dim": 128,
+    "hidden_dropout": 0.0,
+    "hidden_size": 3136,
+    "hybrid_override_pattern": "M-M-M-MM-M-M*-M-M*-M-M-M*-M-M-MM*-MMM-M-M-",
+    "initializer_range": 0.02,
+    "intermediate_size": 12544,
+    "layer_norm_epsilon": 1e-05,
+    "mamba_head_dim": 80,
+    "mamba_hidden_act": "silu",
+    "mamba_num_heads": 96,
+    "mamba_proj_bias": false,
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "mlp_hidden_act": "relu2",
+    "model_name": "unsloth/NVIDIA-Nemotron-3-Nano-4B",
+    "model_type": "nemotron_h",
+    "n_groups": 8,
+    "num_attention_heads": 40,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 8,
+    "num_logits_to_keep": 1,
+    "pad_token_id": 999,
+    "rescale_prenorm_residual": true,
+    "residual_in_fp32": false,
+    "rms_norm_eps": 1e-05,
+    "sliding_window": null,
+    "ssm_state_size": 128,
+    "tie_word_embeddings": false,
+    "time_step_floor": 0.0001,
+    "time_step_limit": [
+        0.0,
+        Infinity
+    ],
+    "time_step_max": 0.1,
+    "time_step_min": 0.001,
+    "time_step_rank": 256,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.6.1",
+    "use_bias": false,
+    "use_cache": true,
+    "use_conv_bias": true,
+    "use_mamba_kernels": true,
+    "vocab_size": 131072
+}