Upload folder using huggingface_hub

config.json

@@ -1,88 +1 @@
-{
-  "architectures": [
-    "GptOssForCausalLM"
-  ],
-  "attention_bias": true,
-  "attention_dropout": 0.0,
-  "eos_token_id": 200002,
-  "experts_per_token": 4,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2880,
-  "initial_context_length": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 2880,
-  "layer_types": [
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 131072,
-  "model_type": "gpt_oss",
-  "num_attention_heads": 64,
-  "num_experts_per_tok": 4,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 8,
-  "num_local_experts": 128,
-  "output_router_logits": false,
-  "pad_token_id": 199999,
-  "quantization_config": {
-    "modules_to_not_convert": [
-      "model.layers.*.self_attn",
-      "model.layers.*.mlp.router",
-      "model.embed_tokens",
-      "lm_head"
-    ],
-    "quant_method": "mxfp4"
-  },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "beta_fast": 32.0,
-    "beta_slow": 1.0,
-    "factor": 32.0,
-    "original_max_position_embeddings": 4096,
-    "rope_type": "yarn",
-    "truncate": false
-  },
-  "rope_theta": 150000,
-  "router_aux_loss_coef": 0.9,
-  "sliding_window": 128,
-  "swiglu_limit": 7.0,
-  "tie_word_embeddings": false,
-  "transformers_version": "4.55.0.dev0",
-  "use_cache": true,
-  "vocab_size": 201088
-}
+{"num_hidden_layers": 36, "num_experts": 128, "experts_per_token": 4, "vocab_size": 201088, "hidden_size": 2880, "intermediate_size": 2880, "swiglu_limit": 7.0, "head_dim": 64, "num_attention_heads": 64, "num_key_value_heads": 8, "sliding_window": 128, "initial_context_length": 4096, "rope_theta": 150000, "rope_scaling_factor": 32.0, "rope_ntk_alpha": 1, "rope_ntk_beta": 32}

dtypes.json

@@ -0,0 +1 @@
+{"embedding.weight": "BF16", "block.0.attn.norm.scale": "BF16", "block.0.attn.qkv.weight": "BF16", "block.0.attn.qkv.bias": "BF16", "block.0.attn.sinks": "BF16", "block.0.attn.out.weight": "BF16", "block.0.attn.out.bias": "BF16", "block.0.mlp.norm.scale": "BF16", "block.0.mlp.gate.weight": "BF16", "block.0.mlp.gate.bias": "BF16", "block.0.mlp.mlp1_weight.blocks": "FP4", "block.0.mlp.mlp1_weight.scales": "UE8", "block.0.mlp.mlp1_bias": "BF16", "block.0.mlp.mlp2_weight.blocks": "FP4", "block.0.mlp.mlp2_weight.scales": "UE8", "block.0.mlp.mlp2_bias": "BF16", "block.1.attn.norm.scale": "BF16", "block.1.attn.qkv.weight": "BF16", "block.1.attn.qkv.bias": "BF16", "block.1.attn.sinks": "BF16", "block.1.attn.out.weight": "BF16", "block.1.attn.out.bias": "BF16", "block.1.mlp.norm.scale": "BF16", "block.1.mlp.gate.weight": "BF16", "block.1.mlp.gate.bias": "BF16", "block.1.mlp.mlp1_weight.blocks": "FP4", "block.1.mlp.mlp1_weight.scales": "UE8", "block.1.mlp.mlp1_bias": "BF16", "block.1.mlp.mlp2_weight.blocks": "FP4", "block.1.mlp.mlp2_weight.scales": "UE8", "block.1.mlp.mlp2_bias": "BF16", "block.2.attn.norm.scale": "BF16", "block.2.attn.qkv.weight": "BF16", "block.2.attn.qkv.bias": "BF16", "block.2.attn.sinks": "BF16", "block.2.attn.out.weight": "BF16", "block.2.attn.out.bias": "BF16", "block.2.mlp.norm.scale": "BF16", "block.2.mlp.gate.weight": "BF16", "block.2.mlp.gate.bias": "BF16", "block.2.mlp.mlp1_weight.blocks": "FP4", "block.2.mlp.mlp1_weight.scales": "UE8", "block.2.mlp.mlp1_bias": "BF16", "block.2.mlp.mlp2_weight.blocks": "FP4", "block.2.mlp.mlp2_weight.scales": "UE8", "block.2.mlp.mlp2_bias": "BF16", "block.3.attn.norm.scale": "BF16", "block.3.attn.qkv.weight": "BF16", "block.3.attn.qkv.bias": "BF16", "block.3.attn.sinks": "BF16", "block.3.attn.out.weight": "BF16", "block.3.attn.out.bias": "BF16", "block.3.mlp.norm.scale": "BF16", "block.3.mlp.gate.weight": "BF16", "block.3.mlp.gate.bias": "BF16", "block.3.mlp.mlp1_weight.blocks": "FP4", "block.3.mlp.mlp1_weight.scales": "UE8", "block.3.mlp.mlp1_bias": "BF16", "block.3.mlp.mlp2_weight.blocks": "FP4", "block.3.mlp.mlp2_weight.scales": "UE8", "block.3.mlp.mlp2_bias": "BF16", "block.4.attn.norm.scale": "BF16", "block.4.attn.qkv.weight": "BF16", "block.4.attn.qkv.bias": "BF16", "block.4.attn.sinks": "BF16", "block.4.attn.out.weight": "BF16", "block.4.attn.out.bias": "BF16", "block.4.mlp.norm.scale": "BF16", "block.4.mlp.gate.weight": "BF16", "block.4.mlp.gate.bias": "BF16", "block.4.mlp.mlp1_weight.blocks": "FP4", "block.4.mlp.mlp1_weight.scales": "UE8", "block.4.mlp.mlp1_bias": "BF16", "block.4.mlp.mlp2_weight.blocks": "FP4", "block.4.mlp.mlp2_weight.scales": "UE8", "block.4.mlp.mlp2_bias": "BF16", "block.5.attn.norm.scale": "BF16", "block.5.attn.qkv.weight": "BF16", "block.5.attn.qkv.bias": "BF16", "block.5.attn.sinks": "BF16", "block.5.attn.out.weight": "BF16", "block.5.attn.out.bias": "BF16", "block.5.mlp.norm.scale": "BF16", "block.5.mlp.gate.weight": "BF16", "block.5.mlp.gate.bias": "BF16", "block.5.mlp.mlp1_weight.blocks": "FP4", "block.5.mlp.mlp1_weight.scales": "UE8", "block.5.mlp.mlp1_bias": "BF16", "block.5.mlp.mlp2_weight.blocks": "FP4", "block.5.mlp.mlp2_weight.scales": "UE8", "block.5.mlp.mlp2_bias": "BF16", "block.6.attn.norm.scale": "BF16", "block.6.attn.qkv.weight": "BF16", "block.6.attn.qkv.bias": "BF16", "block.6.attn.sinks": "BF16", "block.6.attn.out.weight": "BF16", "block.6.attn.out.bias": "BF16", "block.6.mlp.norm.scale": "BF16", "block.6.mlp.gate.weight": "BF16", "block.6.mlp.gate.bias": "BF16", "block.6.mlp.mlp1_weight.blocks": "FP4", "block.6.mlp.mlp1_weight.scales": "UE8", "block.6.mlp.mlp1_bias": "BF16", "block.6.mlp.mlp2_weight.blocks": "FP4", "block.6.mlp.mlp2_weight.scales": "UE8", "block.6.mlp.mlp2_bias": "BF16", "block.7.attn.norm.scale": "BF16", "block.7.attn.qkv.weight": "BF16", "block.7.attn.qkv.bias": "BF16", "block.7.attn.sinks": "BF16", "block.7.attn.out.weight": "BF16", "block.7.attn.out.bias": "BF16", "block.7.mlp.norm.scale": "BF16", "block.7.mlp.gate.weight": "BF16", "block.7.mlp.gate.bias": "BF16", "block.7.mlp.mlp1_weight.blocks": "FP4", "block.7.mlp.mlp1_weight.scales": "UE8", "block.7.mlp.mlp1_bias": "BF16", "block.7.mlp.mlp2_weight.blocks": "FP4", "block.7.mlp.mlp2_weight.scales": "UE8", "block.7.mlp.mlp2_bias": "BF16", "block.8.attn.norm.scale": "BF16", "block.8.attn.qkv.weight": "BF16", "block.8.attn.qkv.bias": "BF16", "block.8.attn.sinks": "BF16", "block.8.attn.out.weight": "BF16", "block.8.attn.out.bias": "BF16", "block.8.mlp.norm.scale": "BF16", "block.8.mlp.gate.weight": "BF16", "block.8.mlp.gate.bias": "BF16", "block.8.mlp.mlp1_weight.blocks": "FP4", "block.8.mlp.mlp1_weight.scales": "UE8", "block.8.mlp.mlp1_bias": "BF16", "block.8.mlp.mlp2_weight.blocks": "FP4", "block.8.mlp.mlp2_weight.scales": "UE8", "block.8.mlp.mlp2_bias": "BF16", "block.9.attn.norm.scale": "BF16", "block.9.attn.qkv.weight": "BF16", "block.9.attn.qkv.bias": "BF16", "block.9.attn.sinks": "BF16", "block.9.attn.out.weight": "BF16", "block.9.attn.out.bias": "BF16", "block.9.mlp.norm.scale": "BF16", "block.9.mlp.gate.weight": "BF16", "block.9.mlp.gate.bias": "BF16", "block.9.mlp.mlp1_weight.blocks": "FP4", "block.9.mlp.mlp1_weight.scales": "UE8", "block.9.mlp.mlp1_bias": "BF16", "block.9.mlp.mlp2_weight.blocks": "FP4", "block.9.mlp.mlp2_weight.scales": "UE8", "block.9.mlp.mlp2_bias": "BF16", "block.10.attn.norm.scale": "BF16", "block.10.attn.qkv.weight": "BF16", "block.10.attn.qkv.bias": "BF16", "block.10.attn.sinks": "BF16", "block.10.attn.out.weight": "BF16", "block.10.attn.out.bias": "BF16", "block.10.mlp.norm.scale": "BF16", "block.10.mlp.gate.weight": "BF16", "block.10.mlp.gate.bias": "BF16", "block.10.mlp.mlp1_weight.blocks": "FP4", "block.10.mlp.mlp1_weight.scales": "UE8", "block.10.mlp.mlp1_bias": "BF16", "block.10.mlp.mlp2_weight.blocks": "FP4", "block.10.mlp.mlp2_weight.scales": "UE8", "block.10.mlp.mlp2_bias": "BF16", "block.11.attn.norm.scale": "BF16", "block.11.attn.qkv.weight": "BF16", "block.11.attn.qkv.bias": "BF16", "block.11.attn.sinks": "BF16", "block.11.attn.out.weight": "BF16", "block.11.attn.out.bias": "BF16", "block.11.mlp.norm.scale": "BF16", "block.11.mlp.gate.weight": "BF16", "block.11.mlp.gate.bias": "BF16", "block.11.mlp.mlp1_weight.blocks": "FP4", "block.11.mlp.mlp1_weight.scales": "UE8", "block.11.mlp.mlp1_bias": "BF16", "block.11.mlp.mlp2_weight.blocks": "FP4", "block.11.mlp.mlp2_weight.scales": "UE8", "block.11.mlp.mlp2_bias": "BF16", "block.12.attn.norm.scale": "BF16", "block.12.attn.qkv.weight": "BF16", "block.12.attn.qkv.bias": "BF16", "block.12.attn.sinks": "BF16", "block.12.attn.out.weight": "BF16", "block.12.attn.out.bias": "BF16", "block.12.mlp.norm.scale": "BF16", "block.12.mlp.gate.weight": "BF16", "block.12.mlp.gate.bias": "BF16", "block.12.mlp.mlp1_weight.blocks": "FP4", "block.12.mlp.mlp1_weight.scales": "UE8", "block.12.mlp.mlp1_bias": "BF16", "block.12.mlp.mlp2_weight.blocks": "FP4", "block.12.mlp.mlp2_weight.scales": "UE8", "block.12.mlp.mlp2_bias": "BF16", "block.13.attn.norm.scale": "BF16", "block.13.attn.qkv.weight": "BF16", "block.13.attn.qkv.bias": "BF16", "block.13.attn.sinks": "BF16", "block.13.attn.out.weight": "BF16", "block.13.attn.out.bias": "BF16", "block.13.mlp.norm.scale": "BF16", "block.13.mlp.gate.weight": "BF16", "block.13.mlp.gate.bias": "BF16", "block.13.mlp.mlp1_weight.blocks": "FP4", "block.13.mlp.mlp1_weight.scales": "UE8", "block.13.mlp.mlp1_bias": "BF16", "block.13.mlp.mlp2_weight.blocks": "FP4", "block.13.mlp.mlp2_weight.scales": "UE8", "block.13.mlp.mlp2_bias": "BF16", "block.14.attn.norm.scale": "BF16", "block.14.attn.qkv.weight": "BF16", "block.14.attn.qkv.bias": "BF16", "block.14.attn.sinks": "BF16", "block.14.attn.out.weight": "BF16", "block.14.attn.out.bias": "BF16", "block.14.mlp.norm.scale": "BF16", "block.14.mlp.gate.weight": "BF16", "block.14.mlp.gate.bias": "BF16", "block.14.mlp.mlp1_weight.blocks": "FP4", "block.14.mlp.mlp1_weight.scales": "UE8", "block.14.mlp.mlp1_bias": "BF16", "block.14.mlp.mlp2_weight.blocks": "FP4", "block.14.mlp.mlp2_weight.scales": "UE8", "block.14.mlp.mlp2_bias": "BF16", "block.15.attn.norm.scale": "BF16", "block.15.attn.qkv.weight": "BF16", "block.15.attn.qkv.bias": "BF16", "block.15.attn.sinks": "BF16", "block.15.attn.out.weight": "BF16", "block.15.attn.out.bias": "BF16", "block.15.mlp.norm.scale": "BF16", "block.15.mlp.gate.weight": "BF16", "block.15.mlp.gate.bias": "BF16", "block.15.mlp.mlp1_weight.blocks": "FP4", "block.15.mlp.mlp1_weight.scales": "UE8", "block.15.mlp.mlp1_bias": "BF16", "block.15.mlp.mlp2_weight.blocks": "FP4", "block.15.mlp.mlp2_weight.scales": "UE8", "block.15.mlp.mlp2_bias": "BF16", "block.16.attn.norm.scale": "BF16", "block.16.attn.qkv.weight": "BF16", "block.16.attn.qkv.bias": "BF16", "block.16.attn.sinks": "BF16", "block.16.attn.out.weight": "BF16", "block.16.attn.out.bias": "BF16", "block.16.mlp.norm.scale": "BF16", "block.16.mlp.gate.weight": "BF16", "block.16.mlp.gate.bias": "BF16", "block.16.mlp.mlp1_weight.blocks": "FP4", "block.16.mlp.mlp1_weight.scales": "UE8", "block.16.mlp.mlp1_bias": "BF16", "block.16.mlp.mlp2_weight.blocks": "FP4", "block.16.mlp.mlp2_weight.scales": "UE8", "block.16.mlp.mlp2_bias": "BF16", "block.17.attn.norm.scale": "BF16", "block.17.attn.qkv.weight": "BF16", "block.17.attn.qkv.bias": "BF16", "block.17.attn.sinks": "BF16", "block.17.attn.out.weight": "BF16", "block.17.attn.out.bias": "BF16", "block.17.mlp.norm.scale": "BF16", "block.17.mlp.gate.weight": "BF16", "block.17.mlp.gate.bias": "BF16", "block.17.mlp.mlp1_weight.blocks": "FP4", "block.17.mlp.mlp1_weight.scales": "UE8", "block.17.mlp.mlp1_bias": "BF16", "block.17.mlp.mlp2_weight.blocks": "FP4", "block.17.mlp.mlp2_weight.scales": "UE8", "block.17.mlp.mlp2_bias": "BF16", "block.18.attn.norm.scale": "BF16", "block.18.attn.qkv.weight": "BF16", "block.18.attn.qkv.bias": "BF16", "block.18.attn.sinks": "BF16", "block.18.attn.out.weight": "BF16", "block.18.attn.out.bias": "BF16", "block.18.mlp.norm.scale": "BF16", "block.18.mlp.gate.weight": "BF16", "block.18.mlp.gate.bias": "BF16", "block.18.mlp.mlp1_weight.blocks": "FP4", "block.18.mlp.mlp1_weight.scales": "UE8", "block.18.mlp.mlp1_bias": "BF16", "block.18.mlp.mlp2_weight.blocks": "FP4", "block.18.mlp.mlp2_weight.scales": "UE8", "block.18.mlp.mlp2_bias": "BF16", "block.19.attn.norm.scale": "BF16", "block.19.attn.qkv.weight": "BF16", "block.19.attn.qkv.bias": "BF16", "block.19.attn.sinks": "BF16", "block.19.attn.out.weight": "BF16", "block.19.attn.out.bias": "BF16", "block.19.mlp.norm.scale": "BF16", "block.19.mlp.gate.weight": "BF16", "block.19.mlp.gate.bias": "BF16", "block.19.mlp.mlp1_weight.blocks": "FP4", "block.19.mlp.mlp1_weight.scales": "UE8", "block.19.mlp.mlp1_bias": "BF16", "block.19.mlp.mlp2_weight.blocks": "FP4", "block.19.mlp.mlp2_weight.scales": "UE8", "block.19.mlp.mlp2_bias": "BF16", "block.20.attn.norm.scale": "BF16", "block.20.attn.qkv.weight": "BF16", "block.20.attn.qkv.bias": "BF16", "block.20.attn.sinks": "BF16", "block.20.attn.out.weight": "BF16", "block.20.attn.out.bias": "BF16", "block.20.mlp.norm.scale": "BF16", "block.20.mlp.gate.weight": "BF16", "block.20.mlp.gate.bias": "BF16", "block.20.mlp.mlp1_weight.blocks": "FP4", "block.20.mlp.mlp1_weight.scales": "UE8", "block.20.mlp.mlp1_bias": "BF16", "block.20.mlp.mlp2_weight.blocks": "FP4", "block.20.mlp.mlp2_weight.scales": "UE8", "block.20.mlp.mlp2_bias": "BF16", "block.21.attn.norm.scale": "BF16", "block.21.attn.qkv.weight": "BF16", "block.21.attn.qkv.bias": "BF16", "block.21.attn.sinks": "BF16", "block.21.attn.out.weight": "BF16", "block.21.attn.out.bias": "BF16", "block.21.mlp.norm.scale": "BF16", "block.21.mlp.gate.weight": "BF16", "block.21.mlp.gate.bias": "BF16", "block.21.mlp.mlp1_weight.blocks": "FP4", "block.21.mlp.mlp1_weight.scales": "UE8", "block.21.mlp.mlp1_bias": "BF16", "block.21.mlp.mlp2_weight.blocks": "FP4", "block.21.mlp.mlp2_weight.scales": "UE8", "block.21.mlp.mlp2_bias": "BF16", "block.22.attn.norm.scale": "BF16", "block.22.attn.qkv.weight": "BF16", "block.22.attn.qkv.bias": "BF16", "block.22.attn.sinks": "BF16", "block.22.attn.out.weight": "BF16", "block.22.attn.out.bias": "BF16", "block.22.mlp.norm.scale": "BF16", "block.22.mlp.gate.weight": "BF16", "block.22.mlp.gate.bias": "BF16", "block.22.mlp.mlp1_weight.blocks": "FP4", "block.22.mlp.mlp1_weight.scales": "UE8", "block.22.mlp.mlp1_bias": "BF16", "block.22.mlp.mlp2_weight.blocks": "FP4", "block.22.mlp.mlp2_weight.scales": "UE8", "block.22.mlp.mlp2_bias": "BF16", "block.23.attn.norm.scale": "BF16", "block.23.attn.qkv.weight": "BF16", "block.23.attn.qkv.bias": "BF16", "block.23.attn.sinks": "BF16", "block.23.attn.out.weight": "BF16", "block.23.attn.out.bias": "BF16", "block.23.mlp.norm.scale": "BF16", "block.23.mlp.gate.weight": "BF16", "block.23.mlp.gate.bias": "BF16", "block.23.mlp.mlp1_weight.blocks": "FP4", "block.23.mlp.mlp1_weight.scales": "UE8", "block.23.mlp.mlp1_bias": "BF16", "block.23.mlp.mlp2_weight.blocks": "FP4", "block.23.mlp.mlp2_weight.scales": "UE8", "block.23.mlp.mlp2_bias": "BF16", "block.24.attn.norm.scale": "BF16", "block.24.attn.qkv.weight": "BF16", "block.24.attn.qkv.bias": "BF16", "block.24.attn.sinks": "BF16", "block.24.attn.out.weight": "BF16", "block.24.attn.out.bias": "BF16", "block.24.mlp.norm.scale": "BF16", "block.24.mlp.gate.weight": "BF16", "block.24.mlp.gate.bias": "BF16", "block.24.mlp.mlp1_weight.blocks": "FP4", "block.24.mlp.mlp1_weight.scales": "UE8", "block.24.mlp.mlp1_bias": "BF16", "block.24.mlp.mlp2_weight.blocks": "FP4", "block.24.mlp.mlp2_weight.scales": "UE8", "block.24.mlp.mlp2_bias": "BF16", "block.25.attn.norm.scale": "BF16", "block.25.attn.qkv.weight": "BF16", "block.25.attn.qkv.bias": "BF16", "block.25.attn.sinks": "BF16", "block.25.attn.out.weight": "BF16", "block.25.attn.out.bias": "BF16", "block.25.mlp.norm.scale": "BF16", "block.25.mlp.gate.weight": "BF16", "block.25.mlp.gate.bias": "BF16", "block.25.mlp.mlp1_weight.blocks": "FP4", "block.25.mlp.mlp1_weight.scales": "UE8", "block.25.mlp.mlp1_bias": "BF16", "block.25.mlp.mlp2_weight.blocks": "FP4", "block.25.mlp.mlp2_weight.scales": "UE8", "block.25.mlp.mlp2_bias": "BF16", "block.26.attn.norm.scale": "BF16", "block.26.attn.qkv.weight": "BF16", "block.26.attn.qkv.bias": "BF16", "block.26.attn.sinks": "BF16", "block.26.attn.out.weight": "BF16", "block.26.attn.out.bias": "BF16", "block.26.mlp.norm.scale": "BF16", "block.26.mlp.gate.weight": "BF16", "block.26.mlp.gate.bias": "BF16", "block.26.mlp.mlp1_weight.blocks": "FP4", "block.26.mlp.mlp1_weight.scales": "UE8", "block.26.mlp.mlp1_bias": "BF16", "block.26.mlp.mlp2_weight.blocks": "FP4", "block.26.mlp.mlp2_weight.scales": "UE8", "block.26.mlp.mlp2_bias": "BF16", "block.27.attn.norm.scale": "BF16", "block.27.attn.qkv.weight": "BF16", "block.27.attn.qkv.bias": "BF16", "block.27.attn.sinks": "BF16", "block.27.attn.out.weight": "BF16", "block.27.attn.out.bias": "BF16", "block.27.mlp.norm.scale": "BF16", "block.27.mlp.gate.weight": "BF16", "block.27.mlp.gate.bias": "BF16", "block.27.mlp.mlp1_weight.blocks": "FP4", "block.27.mlp.mlp1_weight.scales": "UE8", "block.27.mlp.mlp1_bias": "BF16", "block.27.mlp.mlp2_weight.blocks": "FP4", "block.27.mlp.mlp2_weight.scales": "UE8", "block.27.mlp.mlp2_bias": "BF16", "block.28.attn.norm.scale": "BF16", "block.28.attn.qkv.weight": "BF16", "block.28.attn.qkv.bias": "BF16", "block.28.attn.sinks": "BF16", "block.28.attn.out.weight": "BF16", "block.28.attn.out.bias": "BF16", "block.28.mlp.norm.scale": "BF16", "block.28.mlp.gate.weight": "BF16", "block.28.mlp.gate.bias": "BF16", "block.28.mlp.mlp1_weight.blocks": "FP4", "block.28.mlp.mlp1_weight.scales": "UE8", "block.28.mlp.mlp1_bias": "BF16", "block.28.mlp.mlp2_weight.blocks": "FP4", "block.28.mlp.mlp2_weight.scales": "UE8", "block.28.mlp.mlp2_bias": "BF16", "block.29.attn.norm.scale": "BF16", "block.29.attn.qkv.weight": "BF16", "block.29.attn.qkv.bias": "BF16", "block.29.attn.sinks": "BF16", "block.29.attn.out.weight": "BF16", "block.29.attn.out.bias": "BF16", "block.29.mlp.norm.scale": "BF16", "block.29.mlp.gate.weight": "BF16", "block.29.mlp.gate.bias": "BF16", "block.29.mlp.mlp1_weight.blocks": "FP4", "block.29.mlp.mlp1_weight.scales": "UE8", "block.29.mlp.mlp1_bias": "BF16", "block.29.mlp.mlp2_weight.blocks": "FP4", "block.29.mlp.mlp2_weight.scales": "UE8", "block.29.mlp.mlp2_bias": "BF16", "block.30.attn.norm.scale": "BF16", "block.30.attn.qkv.weight": "BF16", "block.30.attn.qkv.bias": "BF16", "block.30.attn.sinks": "BF16", "block.30.attn.out.weight": "BF16", "block.30.attn.out.bias": "BF16", "block.30.mlp.norm.scale": "BF16", "block.30.mlp.gate.weight": "BF16", "block.30.mlp.gate.bias": "BF16", "block.30.mlp.mlp1_weight.blocks": "FP4", "block.30.mlp.mlp1_weight.scales": "UE8", "block.30.mlp.mlp1_bias": "BF16", "block.30.mlp.mlp2_weight.blocks": "FP4", "block.30.mlp.mlp2_weight.scales": "UE8", "block.30.mlp.mlp2_bias": "BF16", "block.31.attn.norm.scale": "BF16", "block.31.attn.qkv.weight": "BF16", "block.31.attn.qkv.bias": "BF16", "block.31.attn.sinks": "BF16", "block.31.attn.out.weight": "BF16", "block.31.attn.out.bias": "BF16", "block.31.mlp.norm.scale": "BF16", "block.31.mlp.gate.weight": "BF16", "block.31.mlp.gate.bias": "BF16", "block.31.mlp.mlp1_weight.blocks": "FP4", "block.31.mlp.mlp1_weight.scales": "UE8", "block.31.mlp.mlp1_bias": "BF16", "block.31.mlp.mlp2_weight.blocks": "FP4", "block.31.mlp.mlp2_weight.scales": "UE8", "block.31.mlp.mlp2_bias": "BF16", "block.32.attn.norm.scale": "BF16", "block.32.attn.qkv.weight": "BF16", "block.32.attn.qkv.bias": "BF16", "block.32.attn.sinks": "BF16", "block.32.attn.out.weight": "BF16", "block.32.attn.out.bias": "BF16", "block.32.mlp.norm.scale": "BF16", "block.32.mlp.gate.weight": "BF16", "block.32.mlp.gate.bias": "BF16", "block.32.mlp.mlp1_weight.blocks": "FP4", "block.32.mlp.mlp1_weight.scales": "UE8", "block.32.mlp.mlp1_bias": "BF16", "block.32.mlp.mlp2_weight.blocks": "FP4", "block.32.mlp.mlp2_weight.scales": "UE8", "block.32.mlp.mlp2_bias": "BF16", "block.33.attn.norm.scale": "BF16", "block.33.attn.qkv.weight": "BF16", "block.33.attn.qkv.bias": "BF16", "block.33.attn.sinks": "BF16", "block.33.attn.out.weight": "BF16", "block.33.attn.out.bias": "BF16", "block.33.mlp.norm.scale": "BF16", "block.33.mlp.gate.weight": "BF16", "block.33.mlp.gate.bias": "BF16", "block.33.mlp.mlp1_weight.blocks": "FP4", "block.33.mlp.mlp1_weight.scales": "UE8", "block.33.mlp.mlp1_bias": "BF16", "block.33.mlp.mlp2_weight.blocks": "FP4", "block.33.mlp.mlp2_weight.scales": "UE8", "block.33.mlp.mlp2_bias": "BF16", "block.34.attn.norm.scale": "BF16", "block.34.attn.qkv.weight": "BF16", "block.34.attn.qkv.bias": "BF16", "block.34.attn.sinks": "BF16", "block.34.attn.out.weight": "BF16", "block.34.attn.out.bias": "BF16", "block.34.mlp.norm.scale": "BF16", "block.34.mlp.gate.weight": "BF16", "block.34.mlp.gate.bias": "BF16", "block.34.mlp.mlp1_weight.blocks": "FP4", "block.34.mlp.mlp1_weight.scales": "UE8", "block.34.mlp.mlp1_bias": "BF16", "block.34.mlp.mlp2_weight.blocks": "FP4", "block.34.mlp.mlp2_weight.scales": "UE8", "block.34.mlp.mlp2_bias": "BF16", "block.35.attn.norm.scale": "BF16", "block.35.attn.qkv.weight": "BF16", "block.35.attn.qkv.bias": "BF16", "block.35.attn.sinks": "BF16", "block.35.attn.out.weight": "BF16", "block.35.attn.out.bias": "BF16", "block.35.mlp.norm.scale": "BF16", "block.35.mlp.gate.weight": "BF16", "block.35.mlp.gate.bias": "BF16", "block.35.mlp.mlp1_weight.blocks": "FP4", "block.35.mlp.mlp1_weight.scales": "UE8", "block.35.mlp.mlp1_bias": "BF16", "block.35.mlp.mlp2_weight.blocks": "FP4", "block.35.mlp.mlp2_weight.scales": "UE8", "block.35.mlp.mlp2_bias": "BF16", "norm.scale": "BF16", "unembedding.weight": "BF16"}

model--00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3
+size 10544040680

model--00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b8f0d5c7dc3195c61a711d08384a1f85624f018186da541585c0f97ac61020
+size 10488721680

model--00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbccd746d50e9543e8016d0a43ab4487c7f86d72349b1ef17abdfec509d0701
+size 10488721688

model--00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc73cf6d18f96a2e62428758463157cc12768f410873152a50d3929a64cd049
+size 10488721672

model--00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15fd69843e9cc6fdf2db0efe0cf0979b49a6ba84b3a38169b2fabc5479d04a7d
+size 10488721680

model--00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aedef2ee0a5a78a003b3f74fd6883033946b80097bf41e4f4715d95066f0588
+size 10433402600

model--00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d5dfcad1ed6c50aa3c0da7d3f08828dba72b5f58686a987bf3a8f01659cda6
+size 2316539800

model.safetensors.index.json

@@ -1 +1,550 @@
-{"metadata": {"total_size": 65248815744}, "weight_map": {"model.layers.25.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_scales": "model-00000-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.o_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.sinks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.router.bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.router.weight": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_scales": "model-00000-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.o_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.sinks": "model-00000-of-00014.safetensors", "model.layers.27.mlp.router.bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.router.weight": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_scales": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_scales": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.3.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.3.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_scales": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.o_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.sinks": "model-00002-of-00014.safetensors", "model.layers.30.mlp.router.bias": "model-00002-of-00014.safetensors", "model.layers.30.mlp.router.weight": "model-00002-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_scales": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.sinks": "model-00002-of-00014.safetensors", "model.layers.20.mlp.router.bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.router.weight": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.23.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.23.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_scales": "model-00004-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.o_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.sinks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.router.bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.router.weight": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_scales": "model-00004-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.o_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.sinks": "model-00004-of-00014.safetensors", "model.layers.25.mlp.router.bias": "model-00004-of-00014.safetensors", "model.layers.25.mlp.router.weight": "model-00004-of-00014.safetensors", "model.layers.25.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.7.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.7.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_scales": "model-00006-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.sinks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.router.bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.router.weight": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_scales": "model-00006-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.sinks": "model-00006-of-00014.safetensors", "model.layers.9.mlp.router.bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.router.weight": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.sinks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.router.bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.router.weight": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.sinks": "model-00007-of-00014.safetensors", "model.layers.16.mlp.router.bias": "model-00007-of-00014.safetensors", "model.layers.16.mlp.router.weight": "model-00007-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_scales": "model-00008-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.sinks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.router.bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.router.weight": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_scales": "model-00008-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.sinks": "model-00008-of-00014.safetensors", "model.layers.18.mlp.router.bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.router.weight": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.2.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.2.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.1.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.1.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_scales": "model-00010-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.sinks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.router.bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.router.weight": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_scales": "model-00010-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.sinks": "model-00010-of-00014.safetensors", "model.layers.11.mlp.router.bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.router.weight": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.14.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.14.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.embed_tokens.weight": "model-00012-of-00014.safetensors", "model.norm.weight": "model-00012-of-00014.safetensors", "lm_head.weight": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_blocks": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_scales": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_bias": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_blocks": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_scales": "model-00012-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.sinks": "model-00012-of-00014.safetensors", "model.layers.31.mlp.router.bias": "model-00012-of-00014.safetensors", "model.layers.31.mlp.router.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_bias": "model-00012-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_scales": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.sinks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.router.bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.router.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_scales": "model-00013-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.sinks": "model-00013-of-00014.safetensors", "model.layers.33.mlp.router.bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.router.weight": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_scales": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_scales": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.4.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.4.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors"}}
+{
+  "metadata": {
+    "total_size": 65248815744
+  },
+  "weight_map": {
+    "block.0.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.0.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.0.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.0.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.0.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.0.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.0.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.0.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.0.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.1.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.1.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.1.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.1.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.1.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.1.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.1.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.1.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.1.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.10.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.10.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.10.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.10.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.10.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.10.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.10.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.10.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.10.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.11.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.11.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.11.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.11.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.11.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.11.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.11.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.11.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.11.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.12.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.12.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.12.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.12.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.12.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.12.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.12.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.12.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.12.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.13.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.13.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.13.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.13.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.13.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.13.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.13.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.13.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.13.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.14.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.14.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.14.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.14.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.14.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.14.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.14.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.14.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.14.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.14.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.14.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.15.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.15.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.15.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.15.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.15.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.15.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.15.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.15.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.15.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.16.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.16.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.16.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.16.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.16.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.16.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.16.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.16.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.16.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.17.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.17.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.17.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.17.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.17.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.17.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.17.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.17.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.17.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.18.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.18.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.18.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.18.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.18.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.18.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.18.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.18.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.18.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.19.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.19.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.19.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.19.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.19.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.19.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.19.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.19.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.19.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.2.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.2.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.2.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.2.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.2.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.2.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.2.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.2.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.2.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.2.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.2.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.20.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.20.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.20.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.20.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.20.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.20.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.20.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.20.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.20.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.21.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.21.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.21.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.21.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.21.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.21.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.21.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.21.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.21.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.22.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.22.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.22.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.22.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.22.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.22.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.22.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.22.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.22.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.23.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.23.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.23.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.23.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.23.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.23.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.23.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.23.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.23.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.24.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.24.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.24.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.24.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.24.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.24.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.24.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.24.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.24.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.25.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.25.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.25.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.25.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.25.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.25.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.25.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.25.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.25.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.25.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.25.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.26.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.26.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.26.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.26.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.26.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.26.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.26.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.26.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.26.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.27.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.27.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.27.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.27.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.27.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.27.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.27.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.27.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.27.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.28.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.28.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.28.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.28.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.28.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.28.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.28.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.28.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.28.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.29.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.29.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.29.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.29.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.29.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.29.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.29.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.29.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.29.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.3.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.3.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.3.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.3.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.3.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.3.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.3.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.3.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.3.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.30.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.30.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.30.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.30.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.30.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.30.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.30.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.30.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.30.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.30.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.30.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.31.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.31.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.31.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.31.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.31.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.31.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.31.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.31.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.31.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.32.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.32.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.32.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.32.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.32.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.32.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.32.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.32.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.32.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.33.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.33.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.33.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.33.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.33.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.33.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.33.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.33.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.33.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.34.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.34.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.34.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.34.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.34.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.34.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.34.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.34.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.34.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.35.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.35.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.35.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.35.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.35.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.35.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.35.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.35.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.35.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.4.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.4.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.4.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.4.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.4.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.4.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.4.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.4.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.4.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.4.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.4.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.5.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.5.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.5.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.5.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.5.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.5.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.5.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.5.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.5.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.6.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.6.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.6.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.6.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.6.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.6.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.6.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.6.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.6.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.7.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.7.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.7.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.7.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.7.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.7.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.7.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.7.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.7.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.8.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.8.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.8.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.8.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.8.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.8.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.8.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.8.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.8.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.9.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.9.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.9.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.9.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.9.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.9.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.9.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.9.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.9.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "embedding.weight": "model--00007-of-00007.safetensors",
+    "norm.scale": "model--00007-of-00007.safetensors",
+    "unembedding.weight": "model--00007-of-00007.safetensors"
+  }
+}