Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cognitivecomputations/WestLake-7B-v2-laser",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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": 4,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,43 @@
+base_model: cognitivecomputations/WestLake-7B-v2-laser
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: mlabonne/Daredevil-7B
+    positive_prompts:
+      - "Answer this question from the ARC (Argument Reasoning Comprehension)."
+      - "Use common sense and logical reasoning skills."
+    negative_prompts:
+      - "nonsense"
+      - "irrational"
+      - "math"
+      - "code"
+  - source_model: cognitivecomputations/WestLake-7B-v2-laser
+    positive_prompts:
+      - "Answer this question from the Winogrande test."
+      - "Use advanced knowledge of culture and humanity"
+    negative_prompts:
+      - "ignorance"
+      - "uninformed"
+      - "creativity"
+  - source_model: mlabonne/Daredevil-7B
+    positive_prompts:
+      - "Calculate the answer to this math problem"
+      - "My mathematical capabilities are strong, allowing me to handle complex mathematical queries"
+      - "solve for"
+    negative_prompts:
+      - "incorrect"
+      - "inaccurate"
+      - "creativity"
+  - source_model: Treza12/BioMistral-FineTUned81
+    positive_prompts:
+      - "Provide a detailed explanation based on medical literature."
+      - "Apply clinical reasoning to answer this healthcare question."
+      - "Use biomedical knowledge to solve this problem."
+      - "Interpret these clinical findings in the context of patient care."
+      - "Leverage your understanding of healthcare systems to advise on policy."
+    negative_prompts:
+      - "vague"
+      - "non-scientific"
+      - "unrelated to healthcare"
+      - "simplistic understanding"
+      - "ignore clinical guidelines"

model-00001-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9538096537f7577abc0ac960c40c6d045cdb5291c3864ed8a9dc574984a6fd
+size 991970880

model-00002-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35512ca4784512a37f9b2e7815a447607bffb0a15c86ee6fd5fcfdbcc8c4c423
+size 905987800

model-00003-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa526f3f466637961d764e7c9a766275fda31135019f0f9122269f80affa593
+size 998253976

model-00004-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014becdbda9ec2f3753f6b153658c48affb369f2fde1e7eafb3847d866856c33
+size 905979504

model-00005-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79555782d528dba3d42696bde044ffe4f5720a60ec0f9a3df5bc76eac1756909
+size 905987800

model-00006-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe21537508db1586d8eac9d8443680299c34474cd668ce2bfc93bf3e4cc55148
+size 905987800

model-00007-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34f3594a31af77f250184b66590d8cfdaa07776a194591002b18c2c7a80cc8a
+size 939525296

model-00008-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3d89946ba92a2f04a332a5e877c26b01891ab4891601e59627262343fa6763
+size 905987800

model-00009-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7fba2a911799be1ea79662a3aa637998ff0320c17afd92c5b6c1221b0c9c485
+size 905987800

model-00010-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59775440397c04f3f01b2f5ef393656827a8103ec0574692316f7b65eb2d1d49
+size 939525296

model-00011-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1634f99aac8ad6d717570c9af27417010e17ae54b427aac69628a3bb3661f42
+size 905987800

model-00012-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73f569abf34c02dde0d6fb6d4aaf803090647dc735f8b0ab29582fbb2aaf4a3
+size 905987800

model-00013-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bbc860585f2defe0e9179d84f47a02bcd883747ff30f2060c506f877b53445
+size 998253976

model-00014-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2622bacccc22673a5cb2fd0f6f29331863a6dd654ef5c139378dc65fda54d723
+size 905979504

model-00015-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321f6c613f217a0568f01d7aab797ddff5b19869186e77a640d25f9615e56dd7
+size 905987816

model-00016-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53607a83e9e054c24581603c5a975dad55d355bd715b0a9fb985272cd8597e66
+size 905987816

model-00017-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3dc667a93bf76ef74c955d596e53828835e8e3d2a1458efeae62cd68df65f62
+size 939525304

model-00018-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1022fcf6025b45ec3c03122645ae4fa8e9cbc35392d9f9f9c4e374bdbec343df
+size 905987816

model-00019-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f12793e4cc6e5fb4a8ea0b12a6d10d2aaaea82b8f58b0e31382263193f982f
+size 905987816

model-00020-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4644aa772f0e9a3b5bf9e029aa1b8f40472af57fd1b174b3c68c6f5926a1b817
+size 939525304

model-00021-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0cdc7bfd479bfa8b727d052be5ff9425f31b400aebb538016457b6a5a0a62b
+size 905987816

model-00022-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14778d881b3dd7a2425a72cff492abb8479168fc91b250a9754dd7a5b9ef6c8d
+size 905987816

model-00023-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3b835c9769d00072d204cb078ffda2cc623376930cb1ec890bfcd283646d22
+size 998253992

model-00024-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3857013aeacaffe4460fc68ae0917753114b1247e4487c9a1e2da4d013ba9e64
+size 905979512

model-00025-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc46abe47a4cc6278bc15acbb02194df7a84f81c656d65857c7d0dca5f7243f
+size 905987816

model-00026-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e658d0e1eb9792585d0837130a12a0f6f1757e83a8f364ba5a31dcdf7bc8e04f
+size 905987816

model-00027-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284b03b2b535f6c9895702ec2a52afa80913ec5e9fadd2b5665b007f6059b162
+size 939525304

model-00028-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af5b19fb91b62e5ac35237386da37ea76be2409cac2d0b37089108e69b030f5
+size 905987816

model-00029-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802607812342f1fa55349bd034c9a87c5ca49c59527987a43eea36803f362084
+size 905987816

model-00030-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc449f0293ead5a53fd01e9e6ad3c18ae874561ab76c2b053a473a121ef40bf
+size 939525304

model-00031-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ef25ff2ceb094eed70712fabae72c68f0c0022faed4189f402f4bbfa8fdc71
+size 905987816

model-00032-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d995c30e660e38d9b1a6763ef8f276ecc796363e77520def4d9766fa927fc7
+size 905987816

model-00033-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c2bad25a05dd6d8a82aca949cafdd6b4385c2c59b7ea63f6e6f6cb97d8ab7f
+size 998253992

model-00034-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1542f069f447779d508cb9f82deec34a108b7e5a57255ab641bbe885fec1d0
+size 905979512

model-00035-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e87725d76a89d8c11c218b21da5f921a9601a8f9b74c7c8c91bfa398d355e8
+size 905987816

model-00036-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d274a406ea7e671ecd86797f4de2f27bfc60af72f67deb4c32fb3186caa8f9c3
+size 905987816

model-00037-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91208ec699e71ca2fbc354cf465f4c40ff9ae5313be726c82ad71cdeff6d972
+size 939525304

model-00038-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b276b8cebe9b7b2fd87094750525b8c69a7c3da832791ede29b75a7bfef67ee3
+size 905987816

model-00039-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117c61e712714f28daa261672fd1a5e557f6bb8ec4cd55969361b6ca2333f09b
+size 905987816

model-00040-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368a2f9395b7396ea879395d7f14926341fa8d2a05a3e256206ee9f4ab4b6edf
+size 939525304

model-00041-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257b80c6efe52e2d7669e153cca2bd466947f51ff110ac8b97d3cd886368f95c
+size 905987816

model-00042-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f5a359a06c02dde13e4dfb7639637a8eb121f460130aa561a091bebcb126e9
+size 905987816

model-00043-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e73daf0796c6c55acbe3312955fee01100b0421ec938861d10502595ab0caa
+size 998253992

model-00044-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f33b8b0c4bbcef5c99c524efdf7b4da1af67a2d83ccc49eda727b9d50dc3ce
+size 905979512

model-00045-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dddf3186bf2c604381e5868c5a5787949dac14e00cf97ab9476a7260d29d92d
+size 905987816

model-00046-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a385a994c8a16f9bdb5f3b698e33174aba533d51fd600d0f7049eb58e91c9d6
+size 822092944

model-00047-of-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8826e242d30668553797466681adcedb741860932180eed54f9751045c65048
+size 263196472

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 42670235648}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00047.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00047.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00047.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00047.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00047.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00047.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00047.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00047.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00047.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00047.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00047.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00047.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00047.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00047.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00047.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00047.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00047.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00047.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00047.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00047.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00047.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00047.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00047.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00047.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00047.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00047.safetensors", "model.layers.8.input_layernorm.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00047.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00047.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00047.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00047.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00047.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00047.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00047.safetensors", "model.layers.10.input_layernorm.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00015-of-00047.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00047.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00047.safetensors", "model.layers.11.input_layernorm.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00016-of-00047.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00016-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00047.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00047.safetensors", "model.layers.12.input_layernorm.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00018-of-00047.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00047.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00047.safetensors", "model.layers.13.input_layernorm.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00047.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00019-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00047.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00047.safetensors", "model.layers.14.input_layernorm.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00021-of-00047.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00047.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00047.safetensors", "model.layers.15.input_layernorm.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00022-of-00047.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00022-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00047.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00047.safetensors", "model.layers.16.input_layernorm.weight": "model-00023-of-00047.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00024-of-00047.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00047.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00047.safetensors", "model.layers.17.input_layernorm.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00025-of-00047.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00047.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00047.safetensors", "model.layers.18.input_layernorm.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00026-of-00047.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00026-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00047.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00047.safetensors", "model.layers.19.input_layernorm.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00028-of-00047.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00047.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00047.safetensors", "model.layers.20.input_layernorm.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00029-of-00047.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00029-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00047.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00047.safetensors", "model.layers.21.input_layernorm.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00031-of-00047.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00047.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00047.safetensors", "model.layers.22.input_layernorm.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00032-of-00047.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00032-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00047.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00047.safetensors", "model.layers.23.input_layernorm.weight": "model-00033-of-00047.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00034-of-00047.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00047.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00047.safetensors", "model.layers.24.input_layernorm.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00035-of-00047.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00047.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00047.safetensors", "model.layers.25.input_layernorm.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00036-of-00047.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00036-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00047.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00047.safetensors", "model.layers.26.input_layernorm.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00038-of-00047.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00047.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00047.safetensors", "model.layers.27.input_layernorm.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00039-of-00047.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00039-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00047.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00047.safetensors", "model.layers.28.input_layernorm.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00041-of-00047.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00041-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00047.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00047.safetensors", "model.layers.29.input_layernorm.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00042-of-00047.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00042-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00047.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00047.safetensors", "model.layers.30.input_layernorm.weight": "model-00043-of-00047.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00044-of-00047.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00044-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00047.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00047.safetensors", "model.layers.31.input_layernorm.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00045-of-00047.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00046-of-00047.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00047.safetensors", "model.norm.weight": "model-00046-of-00047.safetensors", "lm_head.weight": "model-00047-of-00047.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00047-of-00047.safetensors"}}