senseable commited on
Commit
ba8d99f
1 Parent(s): e25cfab

Initial commit

Browse files
.DS_Store ADDED
Binary file (8.2 kB). View file
 
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.gguf filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "senseable/moe-x33",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32014,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 7168,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 19200,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 56,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 62,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": {
25
+ "factor": 4.0,
26
+ "type": "linear"
27
+ },
28
+ "rope_theta": 100000,
29
+ "router_aux_loss_coef": 0.001,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.36.1",
34
+ "use_cache": true,
35
+ "vocab_size": 32256
36
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3dba5dde78cd868301fc5185b1e145228251aaa29fcb34e6266a12f12cf43e7
3
+ size 9733796960
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6300ae5d8cd6d29b34dabbc2b23ec7f34746fab8b94dd111703334fec65d1d
3
+ size 9909047944
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf05ba4f3982990609c9c41645f9be759525bb9764d2f293ace6e81d9231009
3
+ size 9909047944
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256a4e846e72511e6747fed4e49488cb04588d9e28292408ae455ed0042dc290
3
+ size 9909047928
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd9c28247b5ef9f3f37a219924573c7ac69e79811fd3879235d9e9a19eed72f
3
+ size 9909047944
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26c6c95608d55edd1cd4df75f7a5dbd6472feca7f87359d98a96713dfd76c16
3
+ size 9909047944
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec4c7e0ef496fca159c6219bbd9be8a1898e74ca4e44e16534fd11a63d4eb74
3
+ size 9909047944
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa867ec56c454aa6920ab2992fc814e2f03cc751b02e447df6b238be7dd4df0
3
+ size 9909047928
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083a4e20a8e174f149c5df6e766492651cd1f503bfecd133f25e2cfc942c770e
3
+ size 9909047944
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e49dc4886089c67e1193200facb5c9f481695131c11aa9fdc1f9bc79ddaf73
3
+ size 9909047944
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d041b19176bcc055abf5e7e7f9d66b8da9ccb340ef99954903b3b6b6de42d51
3
+ size 9953988048
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b9baf4f1a60e335f5e80b916baacbb2c6b4c500ddd028e681ecac3bd5d64c7
3
+ size 9015366960
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"version": "1.0.0.0"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.norm.weight": "model-00001-of-00012.safetensors", "lm_head.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.57.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.58.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.59.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.60.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.61.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.60.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.60.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.61.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.61.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.60.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.60.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.61.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.61.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.60.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.60.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.61.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.61.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.60.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.61.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|begin▁of▁sentence|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "32000": {
6
+ "content": "õ",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "32001": {
14
+ "content": "÷",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "32002": {
22
+ "content": "Á",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32003": {
30
+ "content": "ý",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32004": {
38
+ "content": "À",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32005": {
46
+ "content": "ÿ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32006": {
54
+ "content": "ø",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32007": {
62
+ "content": "ú",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32008": {
70
+ "content": "þ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "32009": {
78
+ "content": "ü",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "32010": {
86
+ "content": "ù",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "32011": {
94
+ "content": "ö",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "32012": {
102
+ "content": "û",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "32013": {
110
+ "content": "<|begin▁of▁sentence|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32014": {
118
+ "content": "<|end▁of▁sentence|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32015": {
126
+ "content": "<|fim▁hole|>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "32016": {
134
+ "content": "<|fim▁begin|>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "32017": {
142
+ "content": "<|fim▁end|>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "32018": {
150
+ "content": "<pad>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "32019": {
158
+ "content": "<|User|>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "32020": {
166
+ "content": "<|Assistant|>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "32021": {
174
+ "content": "<|EOT|>",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "bos_token": "<|begin▁of▁sentence|>",
183
+ "clean_up_tokenization_spaces": false,
184
+ "eos_token": "<|end▁of▁sentence|>",
185
+ "legacy": true,
186
+ "model_max_length": 16384,
187
+ "pad_token": "<|begin▁of▁sentence|>",
188
+ "sp_model_kwargs": {},
189
+ "tokenizer_class": "LlamaTokenizer",
190
+ "unk_token": null,
191
+ "use_default_system_prompt": false
192
+ }