Upload folder using huggingface_hub

config.json

@@ -1,11 +1,10 @@
 {
   "architectures": [
-    "Qwen2MoeForCausalLM"
+    "MixtralForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 31989,
-  "decoder_sparse_step": 1,
   "eos_token_id": 31989,
   "head_dim": 64,
   "hidden_act": "silu",
@@ -13,31 +12,25 @@
   "initializer_range": 0.036084391824351615,
   "intermediate_size": 1920,
   "max_position_embeddings": 8192,
-  "max_window_layers": 28,
   "mlp_bias": false,
-  "mlp_only_layers": [],
-  "model_type": "qwen2_moe",
-  "moe_intermediate_size": 1920,
-  "norm_topk_prob": true,
+  "model_type": "mixtral",
   "num_attention_heads": 12,
-  "num_experts": 3,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 27,
   "num_key_value_heads": 4,
+  "num_local_experts": 4,
   "output_router_logits": false,
   "pad_token_id": 31989,
   "pretraining_tp": 1,
-  "qkv_bias": true,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.001,
-  "shared_expert_intermediate_size": 1920,
+  "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.53.3",
   "use_cache": false,
-  "use_sliding_window": false,
   "vocab_size": 32000
 }

mergekit_moe_config.yml

@@ -1,7 +1,6 @@
 base_model: minpeter/tiny-ko-187m-base-250725
 gate_mode: hidden
 dtype: bfloat16
-architecture: qwen
 experts:
   - source_model: minpeter/tiny-ko-187m-base-250725
     positive_prompts:
@@ -15,7 +14,6 @@ experts:
       - "[Genres: Science Fiction]\n[Tags: humor, old school, sci fi]"
       - "> get ye flask"
       - "[Mode: Interactive Storyteller]"
-shared_experts:
   - source_model: minpeter/tiny-ko-187m-base-250725
     positive_prompts:
       - "<|im_start|>user\nWie geht es dir?<|im_end|>"

mixtral-patch.py

@@ -0,0 +1,187 @@
+# Copyright (C) 2025 Arcee AI
+#
+# This software is free software: you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This software is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with this program. If not, see http://www.gnu.org/licenses/.
+
+import logging
+from typing import List, Optional
+
+import torch
+import tqdm
+import transformers
+
+from mergekit.architecture import MISTRAL_INFO, WeightInfo
+from mergekit.moe.arch import MoEOutputArchitecture
+from mergekit.moe.common import copy_tensor_out, initialize_io, select_dtype
+from mergekit.moe.config import MoEMergeConfig
+from mergekit.options import MergeOptions
+
+
+class MixtralMoE(MoEOutputArchitecture):
+    def name(self) -> str:
+        return "Mixtral"
+
+    def supports_config(
+        self,
+        config: MoEMergeConfig,
+        explain: bool = False,
+        trust_remote_code: bool = False,
+    ) -> bool:
+        if config.shared_experts:
+            if explain:
+                logging.warning("Mixtral does not support shared experts")
+            return False
+
+        model_types = []
+        for model_ref in [config.base_model] + [e.source_model for e in config.experts]:
+            model_cfg = model_ref.config(trust_remote_code=trust_remote_code)
+            model_types.append(model_cfg.model_type)
+
+        if len(set(model_types)) != 1:
+            if explain:
+                logging.warning(
+                    "Mixtral requires all input models to have the same architecture"
+                )
+            return False
+        if model_types[0] not in ("llama", "mistral"):
+            if explain:
+                logging.warning(
+                    "Mixtral requires all input models to be Llama or Mistral models"
+                )
+            return False
+        return True
+
+    def _generate_config(
+        self,
+        base_config: transformers.PretrainedConfig,
+        num_experts: int,
+        shared_experts: Optional[int] = None,
+        experts_per_token: Optional[int] = None,
+    ) -> transformers.PretrainedConfig:
+        if shared_experts:
+            raise NotImplementedError("Shared experts not supported for Mixtral output")
+
+        if not isinstance(base_config, transformers.MistralConfig):
+            base_cfg_mistral = transformers.MistralConfig(**base_config.to_dict())
+            base_cfg_mistral.sliding_window = None
+            base_cfg_mistral.max_position_embeddings = (
+                base_config.max_position_embeddings
+            )
+            base_config = base_cfg_mistral
+
+        out_cfg = transformers.MixtralConfig(**base_config.to_dict())
+        out_cfg.architectures = ["MixtralForCausalLM"]
+        out_cfg.num_local_experts = num_experts
+        out_cfg.num_experts_per_tok = experts_per_token or 2
+        out_cfg.sliding_window = None
+
+        if (out_cfg.num_local_experts & (out_cfg.num_local_experts - 1)) != 0:
+            logging.warning(
+                f"Your model has {out_cfg.num_local_experts} experts, which is "
+                "not a power of two. The model will not be usable in llama.cpp."
+            )
+        return out_cfg
+
+    def _remap_weight_name(self, weight: WeightInfo) -> str:
+        if ".mlp." not in weight.name:
+            # Everything but MLP is identical to base Mistral
+            return weight.name
+
+        res = weight.name
+        for needle, replacement in [
+            (".mlp.gate_proj", ".block_sparse_moe.experts.{expert_idx}.w1"),
+            (".mlp.down_proj", ".block_sparse_moe.experts.{expert_idx}.w2"),
+            (".mlp.up_proj", ".block_sparse_moe.experts.{expert_idx}.w3"),
+        ]:
+            res = res.replace(needle, replacement)
+        return res
+
+    def _router_weight_name(self, layer_idx: int) -> str:
+        return f"model.layers.{layer_idx}.block_sparse_moe.gate.weight"
+
+    def write_model(
+        self,
+        out_path: str,
+        config: MoEMergeConfig,
+        merge_options: MergeOptions,
+        router_weights: List[torch.Tensor],
+        shared_router_weights: Optional[List[torch.Tensor]] = None,
+    ):
+        base_model = config.base_model
+        base_cfg = base_model.config(trust_remote_code=merge_options.trust_remote_code)
+
+        assert len(router_weights) == base_cfg.num_hidden_layers, (
+            f"Expected {base_cfg.num_hidden_layers} router weights, "
+            f"got {len(router_weights)}"
+        )
+
+        out_dtype = select_dtype(config, base_cfg)
+        out_cfg = self._generate_config(
+            base_cfg,
+            len(config.experts),
+            len(config.shared_experts or []),
+            config.experts_per_token,
+        )
+        out_cfg.torch_dtype = out_dtype
+        out_cfg.save_pretrained(out_path)
+
+        loaders, base_loader, writer = initialize_io(config, out_path, merge_options)
+        for weight_info in tqdm.tqdm(
+            MISTRAL_INFO.all_weights(base_cfg),
+            desc="Weights",
+        ):
+            tensor_name = self._remap_weight_name(weight_info)
+            if "{expert_idx}" in tensor_name:
+                for expert_index, expert in enumerate(config.experts):
+                    expert_name = tensor_name.replace("{expert_idx}", str(expert_index))
+                    expert_loader = loaders.get(expert.source_model)
+                    copy_tensor_out(
+                        weight_info,
+                        expert_loader,
+                        writer,
+                        expert=expert,
+                        out_dtype=out_dtype,
+                        output_name=expert_name,
+                        clone=merge_options.clone_tensors,
+                        is_residual="down_proj" in tensor_name,
+                    )
+            else:
+                # START FINAL PATCH
+                # Because WeightInfo is a frozen Pydantic model, we cannot modify it.
+                # We must manually load and save the tensor for the tied weights case.
+                if (
+                    weight_info.name == "lm_head.weight"
+                    and base_cfg.tie_word_embeddings
+                ):
+                    # If tie_word_embeddings is used, lm_head.weight should not be copied.
+                    pass
+                
+                else:
+                    tensor = base_loader.get_tensor(weight_info.name)
+                    writer.save_tensor(
+                        weight_info.name,  # Always save with the correct destination name
+                        tensor.to(dtype=out_dtype),
+                        clone=merge_options.clone_tensors,
+                    )
+                # END FINAL PATCH
+
+        for layer_idx, weight in enumerate(
+            tqdm.tqdm(router_weights, desc="Router weights")
+        ):
+            writer.save_tensor(
+                self._router_weight_name(layer_idx),
+                weight.to(dtype=out_dtype).contiguous(),
+                clone=merge_options.clone_tensors,
+            )
+
+        writer.finalize()

model-00001-of-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c6f18b44ce328ef35438c1da95654bf1fe7dbb0982377d80d7c516d9ba0dd7a
-size 1089993904
+oid sha256:1265c116b469ee3032ca93a959eb6e608c864e094e905c3533e1e89c4770e2f4
+size 1089915064

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.6", "total_size": 1089921024}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.2.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.experts.2.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.gate.weight": "model-00001-of-00001.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00001-of-00001.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 1089851904}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00001-of-00001.safetensors"}}