model upload

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "GraniteMoeHybridForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12,
+  "eos_token_id": 0,
+  "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": 4096,
+  "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": 62,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "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,
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57be0ebde7435317126232ee9b64f3bd35fb5f511a143550430f91ae7a8e52f2
+size 4916677832

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b525caa43b6fd9011de3200abae3d2444bdfab38cd30ee2a5b5dcf10069f7126
+size 4640615064

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:873bf478522543127f549372b6a7b2b58301c53e2d161dee09c3e16632c01403
+size 4997280664

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2dd493f8779da5d7cc515b5068a3b2e0f9d87753e14c9ab22898c64e94cc829
+size 4880084840

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9bfa543d415b483d2161911a48ea5b0a4dd597a3c130e85c064a3e7b42f6b3
+size 4997280664

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7236571cf1d508871815a560d01bbdd583822e1705e1139d6264fd0a0d57fdfa
+size 2261316064

model.safetensors.index.json

@@ -0,0 +1,593 @@
+{
+  "metadata": {
+    "total_size": 26693187840
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.dt_bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.A_log": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.D": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mamba.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.dt_bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.A_log": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.D": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mamba.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.dt_bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.A_log": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.D": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.out_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mamba.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.conv1d.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.in_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.dt_bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.A_log": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.D": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.out_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mamba.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.conv1d.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.conv1d.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.in_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.dt_bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.A_log": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.D": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.out_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mamba.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.shared_mlp.input_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.shared_mlp.output_linear.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.conv1d.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.in_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.dt_bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.A_log": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.D": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.out_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mamba.norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.router.layer.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.shared_mlp.input_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.shared_mlp.output_linear.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.conv1d.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.conv1d.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.in_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.dt_bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.A_log": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.D": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.out_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mamba.norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.router.layer.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.conv1d.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.conv1d.bias": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.in_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.dt_bias": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.A_log": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.D": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.out_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mamba.norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.conv1d.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.conv1d.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.in_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.dt_bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.A_log": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.D": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.out_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mamba.norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.conv1d.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.conv1d.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.in_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.dt_bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.A_log": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.D": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.out_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mamba.norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.conv1d.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.conv1d.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.in_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.dt_bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.A_log": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.D": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.out_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mamba.norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.conv1d.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.conv1d.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.in_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.dt_bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.A_log": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.D": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.out_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mamba.norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.shared_mlp.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.shared_mlp.output_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.conv1d.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.conv1d.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.in_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.dt_bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.A_log": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.D": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.out_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mamba.norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.router.layer.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.input_linear.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.shared_mlp.input_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.shared_mlp.output_linear.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.conv1d.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.conv1d.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.in_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.dt_bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.A_log": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.D": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.out_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mamba.norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.router.layer.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.conv1d.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.conv1d.bias": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.in_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.dt_bias": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.A_log": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.D": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.out_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mamba.norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.conv1d.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.conv1d.bias": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.in_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.dt_bias": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.A_log": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.D": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.out_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mamba.norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.conv1d.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.conv1d.bias": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.in_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.dt_bias": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.A_log": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.D": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.out_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mamba.norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.conv1d.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.conv1d.bias": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.in_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.dt_bias": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.A_log": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.D": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.out_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mamba.norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.conv1d.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.conv1d.bias": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.in_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.dt_bias": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.A_log": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.D": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.out_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mamba.norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.conv1d.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.conv1d.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.in_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.dt_bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.A_log": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.D": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.out_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mamba.norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.block_sparse_moe.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.shared_mlp.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.shared_mlp.output_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.block_sparse_moe.router.layer.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.block_sparse_moe.input_linear.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.conv1d.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.conv1d.bias": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.in_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.dt_bias": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.A_log": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.D": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mamba.norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.block_sparse_moe.router.layer.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.block_sparse_moe.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.conv1d.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.conv1d.bias": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.in_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.dt_bias": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.A_log": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.D": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mamba.norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.block_sparse_moe.router.layer.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.block_sparse_moe.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.conv1d.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.conv1d.bias": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.in_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.dt_bias": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.A_log": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.D": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mamba.norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.block_sparse_moe.router.layer.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.block_sparse_moe.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.block_sparse_moe.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.shared_mlp.input_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.shared_mlp.output_linear.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.conv1d.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.conv1d.bias": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.in_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.dt_bias": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.A_log": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.D": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.out_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mamba.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,186 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 50304
+}