initial model upload

config.json

@@ -0,0 +1,90 @@
+{
+  "architectures": [
+    "GraniteMoeHybridForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 100257,
+  "embedding_multiplier": 12,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "init_method": "mup",
+  "initializer_range": 0.1,
+  "intermediate_size": 512,
+  "layer_types": [
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba"
+  ],
+  "logits_scaling": 6,
+  "mamba_chunk_size": 256,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 64,
+  "mamba_d_state": 128,
+  "mamba_expand": 2,
+  "mamba_n_groups": 1,
+  "mamba_n_heads": 48,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 131072,
+  "model_type": "granitemoehybrid",
+  "normalization_function": "rmsnorm",
+  "num_attention_heads": 12,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "num_local_experts": 64,
+  "output_router_logits": false,
+  "pad_token_id": 100256,
+  "position_embedding_type": "nope",
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "router_aux_loss_coef": 0.0,
+  "shared_intermediate_size": 1024,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100256,
+  "transformers_version": "4.53.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff219de2a1b3d92897a6866a284fb5817b1e1a62acbd97df314538f34e44b95
+size 4924822608

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:968dc01bcef15155124a2de8a7b128a18384591606aae366fc9f7f8865e2a71e
+size 4879018632

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d525fed75834f785b636bbfa8dea2bf39210a166ff61f69d4c445a05f814a26
+size 4074301016

model.safetensors.index.json

@@ -0,0 +1,594 @@
+{
+  "metadata": {
+    "total_parameters": 6939037248,
+    "total_size": 13878074496
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.block_sparse_moe.router.layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.A_log": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.D": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.conv1d.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.conv1d.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.dt_bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.in_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mamba.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.shared_mlp.input_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.shared_mlp.output_linear.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.block_sparse_moe.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.block_sparse_moe.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.block_sparse_moe.router.layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.A_log": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.D": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.conv1d.bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.conv1d.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.dt_bias": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.in_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mamba.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.shared_mlp.input_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.shared_mlp.output_linear.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.block_sparse_moe.router.layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.A_log": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.D": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.conv1d.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.conv1d.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.dt_bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.in_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mamba.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.shared_mlp.input_linear.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.shared_mlp.output_linear.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

model.sig

@@ -0,0 +1 @@
+{"mediaType": "application/vnd.dev.sigstore.bundle.v0.3+json", "verificationMaterial": {"certificate": {"rawBytes": "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"}, "tlogEntries": [{"logIndex": "541450032", "logId": {"keyId": "wNI9atQGlz+VWfO6LRygH4QUfY/8W4RFwiT5i5WRgB0="}, "kindVersion": {"kind": "dsse", "version": "0.0.1"}, "integratedTime": "1758390904", "inclusionPromise": {"signedEntryTimestamp": "MEUCIQD1AU+iBL5g9mjDhD5HQDvBlTaCP/rIN/G2Xp4wLCuiegIgNE8oXG14CLOph++AzVN3Pa3RWt8jwjG6YYY9Yoy0k7g="}, "inclusionProof": {"logIndex": "419545770", "rootHash": "O/gdR8Cd0kTArNXQL6iRTtMb7a/OTnH4w4iYVdRixrI=", "treeSize": "419545774", "hashes": ["M/4kHXiuz1qMV+yxFvtVOiBveCIyvVSHqk/OUQze5vk=", "4owAPnSYK4Lu7bvyd4wdzGIyef/B+QmUvJq5aGpbKwM=", "Bf20/YfoyQt3pKwm0PkOALnr+VmoMnMbcUZaita3Qo8=", "D9vxayM0lsUtxkOnwOFXDEjfURgP739CJrnpMqojYYE=", "e6Tcj/5fRvkyzJ3yjw6dk47sB641vyA8sAXJcDCSDfs=", "4nOKccRBy25gTI+oW04hDZQfZXVT48M5MVrbePoKkYA=", "wny3t2mjXbTJaShDBTYxFhwB6V7Pn+bGgYrW/yHED5I=", "wjKMAVW/X4cC8VfboYc2Jxn9l72OJX/gQeNxWRSfRlM=", "Foyb9H1nNdEN/TGIleVYO4D5kxSFbF+ZK/iACXMKDUA=", "mdkuXA30wGxXi/WWqyaGXShcgt3T1yYW+lrsZLBFFuo=", "rO8wDSOjmY8VkspFqYaJS4TV5HxywICMlHM8gTxXkAA=", "1mfy94KpcItqshH9+gwqV6jccupcaMpVsF28New8zDY=", "vS7O4ozHIQZJWBiov+mkpI27GE8zAmVCEkRcP3NDyNE="], "checkpoint": {"envelope": "rekor.sigstore.dev - 1193050959916656506\n419545774\nO/gdR8Cd0kTArNXQL6iRTtMb7a/OTnH4w4iYVdRixrI=\n\n\u2014 rekor.sigstore.dev wNI9ajBGAiEA1NbwcosFvOkF2KAme/a+ofIKqZNzy8JaITocCcSLWXUCIQD71RQUyO2D6jUMGQlSvUOCZKvwNbfhgrbhBm7E3CWPvA==\n"}}, "canonicalizedBody": "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"}], "timestampVerificationData": {}}, "dsseEnvelope": {"payload": "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", "payloadType": "application/vnd.in-toto+json", "signatures": [{"sig": "MEUCIQDLiYHNG5wFYl/3GakSKGyoYuMVbFzwgLylPo9RJyaweAIgFzDp60mWElHGeMSL0TqLFfGjBk3YWqJQtWe0ObctQxM="}]}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}