first upload

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Sao10K/Fimbulvetr-11B-v2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,54 @@
+
+base_model: Sao10K/Fimbulvetr-11B-v2
+dtype: bfloat16
+gate_mode: cheap_embed
+experts:
+  - source_model: Sao10K/Fimbulvetr-11B-v2
+    positive_prompts:
+      - "creative"
+      - "storytelling"
+      - "expressive"
+      - "imaginative"
+      - "engaging"
+      - "verbose"
+      - "narrative"
+      - "descriptive"
+      - "elaborate"
+      - "fictional"
+      - "artistic"
+      - "vivid"
+      - "colorful"
+      - "fantastical"
+      - "lyrical"
+
+    negative_prompts:
+      - "sorry"
+      - "I cannot"
+      - "factual"
+      - "concise"
+      - "straightforward"
+      - "objective"
+      - "dry"
+  - source_model: BlueNipples/SnowLotus-v2-10.7B
+    positive_prompts:
+      - "versatile"
+      - "adaptive"
+      - "comprehensive"
+      - "integrated"
+      - "balanced"
+      - "all-rounder"
+      - "flexible"
+      - "wide-ranging"
+      - "multi-disciplinary"
+      - "holistic"
+      - "innovative"
+      - "eclectic"
+      - "resourceful"
+      - "dynamic"
+      - "robust"
+
+    negative_prompts:
+      - "narrow"
+      - "specialized"
+      - "limited"
+      - "focused"

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739c5adc12298c96b42a8a24aa5957f6197f9198787ad5aa92b18dae2a8be988
+size 1933982776

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991bcc6839721bb19c79540f2566d59f3e279d99314f01113225a3886245f90b
+size 1996490960

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a546a362c9cb1e490667faeddb21fdaf8a82fa74f3bcc9edc7be6fccacd561
+size 1996490968

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b064962d0b11789f66ccf6a4e0176ac398b4964e1611c2fce1fc11f4ac5809c
+size 1996490968

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d1cea10fb13af0d40f1364259af5ac729225869b1edd4cb90cb2b21b00249a1
+size 1996490968

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413cc3e05a44bcca5e966bf341f7393f841e46d113f05bce74d8be031fb5b4c4
+size 1996490968

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2839ac6ba20c7e2a246b177ccbcdd894802f33504cffee034eebadf87b7e39
+size 1996490952

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e101371eac46225ea8c03918eaf188199f264d073e7ed77ba5ca27dd8bae96
+size 1996490968

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b337f94e0c3ab6dfda3dece34e8ea16f6496773215a1829c9b88d0bbf28345
+size 1996490968

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9aa376c1c9d9a88a0dfdc8dab60ae04ee11efb010aa86704298fcc5ae7e022
+size 1996490968

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec4301d482f22fbbddb5732b55046a8b5743ddbe272411069a30e151dfe8180
+size 1996490968

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35513ae49b6acdb700892ed035cd94af5b98fd7bc9871f41afe667d28b40cfb
+size 1996490960

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2396331b4889106816b9213caf94ace20bbe256e01dc6e87f7bc5f51009d236a
+size 1996490952

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b5baf46812432e771074af7317d7a5e323c05a5d33bb812aace79ae1c1d138
+size 1996490968

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6d3f6dd07332e829edbcadf9d5b4763232cbf3d781988fc3a33738b820276d
+size 1996490968

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665792df18ae950f90b05ae21257173dc2c92373a06d84ebcc21fd2d81fe8675
+size 1996490968

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d51dfe05847aad3e8787f3c8a77a11f041e6cc6bce3d8b8810cb491c58fe048
+size 1996490968

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b6ac0d37895563f55259861864e5ead663e16cfeb08365a045032147d45514
+size 1980116232

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ffdfd5082a7070b202438d535bd1e10d735a91fd8f6afc7a9d15a7c8793681
+size 1979726824

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71911be421d67575fbe6f9532f825587f854363151f63e9df92802e01808e1f9
+size 537664704

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.norm.weight": "model-00001-of-00020.safetensors", "lm_head.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "<s>",
+  "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": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}