Upload folder using huggingface_hub

config.json

@@ -24,11 +24,10 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "router_aux_loss_coef": 0.001,
-  "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.38.0",
   "use_cache": false,
   "vocab_size": 32000
 }

mergekit_moe_config.yml

@@ -0,0 +1,10 @@
+
+base_model: upstage/SOLAR-10.7B-v1.0
+dtype: float16
+experts:
+  - source_model: upstage/SOLAR-10.7B-Instruct-v1.0
+    positive_prompts: ["당신은 친절한 보편적인 어시스턴트이다."]
+  - source_model: heavytail/kullm-solar
+    positive_prompts: ["당신은 친절한 어시스턴트이다."]
+gate_mode: cheap_embed
+tokenizer_source: base

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4df1050bff41aee32e98027022e6115ccdb3b1059287687f9a33a767da64282
+size 1933982712

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60f02ca57ca8b6640887f6ef3b5ac80241a659b5de578d8645395d3dbf6bf7b
+size 1996490944

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a177fd81b89b52b6f3f4e74682127f95342925cc17834d8b8cfab5d0c9be05c
+size 1996490952

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4eb48b39f332581cdc4ea0c30393f34ce4855f84ac31604b0177db987a629d1
+size 1996490952

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2a0ad9b2624365cf1a5481aca365e3f88dc6bd92987a771c51fb05f1354a77
+size 1996490952

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b627a291b68a094ad709088a5f3227832551428d1557f62bd4ef0854554e5499
+size 1996490952

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bac5d04b24531f68b8772b8138ed2846eac98f21d4ecb95860ecbebc11f471
+size 1996490936

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f317a4a701b43c74b9af32ef4014a562d5f663371f81d0ff8055519adeb19c93
+size 1996490944

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b86d0808a4372261070cfa63678e20d47f322fff440165cf9c1f34f2f219083
+size 1996490952

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17905368c40dd6bca4a11a4a194e0dc4885fba1c86120b9117a9538bbcd2e082
+size 1996490952

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c498a531758e9c5073a7e3546bcc0b7cbe5e50b0dbf7042a39a97439fd57b060
+size 1996490952

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d817a29f459987d9353b1bb0ba5b23db714ed31fa840918f68ac1b2754022b
+size 1996490944

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a591339e61e1f565759146171b3446f3377b34019345557735570b57c186f4
+size 1996490936

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aca0aa072743aad7322e8bbd36f10fdab58b7438944eed58c375f81f3cf7264
+size 1996490952

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e17918c97aa89b077b59db604c6ef0aaf9f78e53f4171185d02d7f0cd17a3eb
+size 1996490952

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337ac4d22e3a1cd045fb6c4fe8e7c06645791e67a78fad6c84943c4df7e31308
+size 1996490952

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb33d0e526f3bd86b3cdc672c403632e81c2ba63639d63a8d636215984af52cc
+size 1996490952

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2266d1b53ea3111fefa7f772f6dfc030274941c28448a0a78593f620d013b4
+size 1980116128

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bc83eaf7b032ced0e8b66171dcc462d2507c6792c4a85ed018577a99c07562
+size 1979726688

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08e384dc4536f4df57f929b64ac008244c0d6a024a7535e44508aee13438286
+size 537664640

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
+}