初始化项目，由ModelHub XC社区提供模型

Model: Zyphra/Zamba2-2.7B-instruct
Source: Original Platform

config.json

@@ -0,0 +1,115 @@
+{
+  "architectures": [
+    "Zamba2ForCausalLM"
+  ],
+  "adapter_rank": 128,
+  "add_bias_linear": false,
+  "attention_dropout": 0.0,
+  "attention_head_dim": 160,
+  "attention_hidden_size": 5120,
+  "bos_token_id": 1,
+  "chunk_size": 256,
+  "eos_token_id": 2,
+  "ffn_hidden_size": 10240,
+  "hidden_act": "gelu",
+  "hidden_size": 2560,
+  "hybrid_layer_ids": [
+    6,
+    12,
+    18,
+    24,
+    30,
+    36,
+    42,
+    47,
+    51
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "kv_channels": 80,
+  "layers_block_type": [
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba",
+    "mamba",
+    "hybrid",
+    "mamba",
+    "mamba"
+  ],
+  "mamba_d_conv": 4,
+  "mamba_d_state": 64,
+  "mamba_expand": 2,
+  "mamba_headdim": 64,
+  "mamba_ngroups": 1,
+  "max_position_embeddings": 4096,
+  "model_type": "zamba2",
+  "n_mamba_heads": 80,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 54,
+  "num_key_value_heads": 32,
+  "num_logits_to_keep": 1,
+  "num_mem_blocks": 2,
+  "num_query_groups": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000,
+  "time_step_floor": 0.0001,
+  "time_step_limit": null,
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_long_context": false,
+  "use_mem_rope": false,
+  "use_shared_attention_adapter": false,
+  "use_shared_mlp_adapter": true,
+  "vocab_size": 32000
+}