Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+base_model: []
+tags:
+- mergekit
+- merge
+
+---
+# vanilla-bagel
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using E:\text-generation-webui\models\Mixtral-8x7B-v0.1 as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* E:\text-generation-webui\models\bagel-8x7b-v0.2
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: E:\text-generation-webui\models\bagel-8x7b-v0.2
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: E:\text-generation-webui\models\Mixtral-8x7B-v0.1
+    parameters:
+      density: 0.5
+      weight: 1
+merge_method: dare_ties
+base_model: E:\text-generation-webui\models\Mixtral-8x7B-v0.1
+parameters:
+  #normalize: false
+  #int8_mask: true
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "E:\\text-generation-webui\\models\\Mixtral-8x7B-v0.1",
+  "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 +1,15 @@
+models:
+  - model: E:\text-generation-webui\models\bagel-8x7b-v0.2
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: E:\text-generation-webui\models\Mixtral-8x7B-v0.1
+    parameters:
+      density: 0.5
+      weight: 1
+merge_method: dare_ties
+base_model: E:\text-generation-webui\models\Mixtral-8x7B-v0.1
+parameters:
+  #normalize: false
+  #int8_mask: true
+dtype: bfloat16

pytorch_model-00001-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f48abdd115c8b5ecd6ad72629f96b6cb14945e625ed54e781601e84d5325792
+size 9942927746

pytorch_model-00002-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107686de11730b0fb8de0236e0ad336d3ce16d8b1ef32fefb8210828d5a9862b
+size 9982809750

pytorch_model-00003-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ead272f0868ec042049f723b6706beb2662a6728e0388eb41876d5930dcf03e
+size 9999502378

pytorch_model-00004-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc353a4b9fb26918fdaf8ecaa1c0fdfb9745689a2266e09da4ab1b7d9a078da
+size 9915699320

pytorch_model-00005-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52ce464ae7b0401fd38b1ebf5f09953b681f5e69538e4af1e709a7d2bd4b1df
+size 9965949096

pytorch_model-00006-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ac7f4cf8dc7c6ed72888a92d6a025d2dc62b5a9c897464fd7b9475dbf93e17
+size 9999585436

pytorch_model-00007-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509e602473aa50cb864e9aefa623b1baedff66e648032a04a9536c34b208439c
+size 9965949048

pytorch_model-00008-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f28774a0ce30c9153ad7acbd740d05d313d96c286b86f11d8ae6b54568f013
+size 9999585460

pytorch_model-00009-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:979c1e9701cb71cc02263575fb3651cc8d1bb2f350470616621c17aac8f3e5e8
+size 9999485490

pytorch_model-00010-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b549b9b978b7f3330a6428778abdee1073815a41d7cc77cbd233c0bdb7e51d3e
+size 3634435370

pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00010.bin", "model.embed_tokens.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00010.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00010.bin", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00010.bin", "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00010.bin", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00010.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00010.bin", "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00010.bin", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00010.bin", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00010.bin", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00010.bin", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00010.bin", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00010.bin", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00010.bin", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00010.bin", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00010.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00009-of-00010.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00010.bin", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00010.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00010.bin", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00010.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00010.bin", "lm_head.weight": "pytorch_model-00010-of-00010.bin", "model.norm.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00010-of-00010.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-00010-of-00010.bin"}}

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
+}