Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+base_model:
+- mistralai/Mixtral-8x7B-v0.1
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+- jondurbin/bagel-dpo-8x7b-v0.2
+- cognitivecomputations/dolphin-2.7-mixtral-8x7b
+- NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss
+- ycros/BagelMIsteryTour-v2-8x7B
+- smelborp/MixtralOrochi8x7B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# maid-yuzu-v8-alter
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+v7's approach worked better than I thought, so I tried something even weirder as a test. I don't think a proper model will come out, but I'm curious about the results.
+
+## Merge Details
+### Merge Method
+
+This model was merged using the SLERP merge method.
+
+This models were merged using the SLERP method in the following order:
+
+    maid-yuzu-v8-base: mistralai/Mixtral-8x7B-v0.1 + mistralai/Mixtral-8x7B-Instruct-v0.1 = 0.5
+    maid-yuzu-v8-step1: above + jondurbin/bagel-dpo-8x7b-v0.2 = 0.25
+    maid-yuzu-v8-step2: above + cognitivecomputations/dolphin-2.7-mixtral-8x7b = 0.25
+    maid-yuzu-v8-step3: above + NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss = 0.25
+    maid-yuzu-v8-step4-alter: above + ycros/BagelMIsteryTour-v2-8x7B = 0.5
+    maid-yuzu-v8-alter: above + smelborp/MixtralOrochi8x7B = 0.5
+
+### Models Merged
+
+The following models were included in the merge:
+* [smelborp/MixtralOrochi8x7B](https://huggingface.co/smelborp/MixtralOrochi8x7B)
+* ../maid-yuzu-v8-step4-alter
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model:
+  model:
+    path: ../maid-yuzu-v8-step4-alter
+dtype: bfloat16
+merge_method: slerp
+parameters:
+  t:
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: ../maid-yuzu-v8-step4-alter
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: smelborp/MixtralOrochi8x7B
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "../maid-yuzu-v8-step4-alter",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+base_model:
+  model:
+    path: ../maid-yuzu-v8-step4-alter
+dtype: bfloat16
+merge_method: slerp
+parameters:
+  t:
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: ../maid-yuzu-v8-step4-alter
+  - layer_range: [0, 32]
+    model:
+      model:
+        path: smelborp/MixtralOrochi8x7B

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00048.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00048.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00048.safetensors", "model.embed_tokens.weight": "model-00003-of-00048.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00048.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00048.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00048.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00048.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00048.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00048.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00048.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00048.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00048.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00048.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00048.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00048.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00048.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00048.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00048.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00048.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00048.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00048.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00048.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00011-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00048.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00048.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00048.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00048.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00048.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00048.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00048.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00048.safetensors", "model.layers.9.input_layernorm.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00048.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00048.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.8.input_layernorm.weight": "model-00016-of-00048.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00016-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00017-of-00048.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00048.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00048.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.10.input_layernorm.weight": "model-00018-of-00048.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00018-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00048.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00048.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00020-of-00048.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.12.input_layernorm.weight": "model-00020-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00021-of-00048.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00048.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00048.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00021-of-00048.safetensors", "model.layers.11.input_layernorm.weight": "model-00021-of-00048.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00021-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00048.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00022-of-00048.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.14.input_layernorm.weight": "model-00022-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00048.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00048.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00023-of-00048.safetensors", "model.layers.13.input_layernorm.weight": "model-00023-of-00048.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00023-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00048.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00048.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00048.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.15.input_layernorm.weight": "model-00026-of-00048.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00026-of-00048.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00027-of-00048.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00027-of-00048.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00027-of-00048.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00048.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00028-of-00048.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.17.input_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00048.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.16.input_layernorm.weight": "model-00028-of-00048.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00028-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00029-of-00048.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00048.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00030-of-00048.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00030-of-00048.safetensors", "model.layers.19.input_layernorm.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00031-of-00048.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00048.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00048.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.18.input_layernorm.weight": "model-00031-of-00048.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00031-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00048.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00032-of-00048.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.21.input_layernorm.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00048.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00048.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.20.input_layernorm.weight": "model-00033-of-00048.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00033-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00034-of-00048.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00036-of-00048.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00048.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00048.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.22.input_layernorm.weight": "model-00036-of-00048.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00036-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00038-of-00048.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00048.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00038-of-00048.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.24.input_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00048.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00048.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.23.input_layernorm.weight": "model-00038-of-00048.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00038-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00048.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00040-of-00048.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00040-of-00048.safetensors", "model.layers.26.input_layernorm.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00048.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00048.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.25.input_layernorm.weight": "model-00041-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00042-of-00048.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00048.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00043-of-00048.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.27.input_layernorm.weight": "model-00043-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00044-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00044-of-00048.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00044-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00048.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00045-of-00048.safetensors", "lm_head.weight": "model-00046-of-00048.safetensors", "model.norm.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00046-of-00048.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.29.input_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00048.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00048.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.28.input_layernorm.weight": "model-00046-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00047-of-00048.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00047-of-00048.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.31.input_layernorm.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00047-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00048-of-00048.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00048-of-00048.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00048-of-00048.safetensors", "model.layers.30.input_layernorm.weight": "model-00048-of-00048.safetensors"}}

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895c85ba39cd9a2fd6e85301b41ff6af2246d62b936f08f6fcf523311cf04099
+size 8589999464

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809a67e88ec6601d193aa65240e7f792c03df6419d95c4ff35a144c26a40c407
+size 8572028256

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c150720e23986720279c97c6dd87076e9063ea52ff15c4eb4386e271bb66765
+size 6450565976

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}