Undi95 commited on
Commit
6b6a11d
1 Parent(s): 11412d0

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jondurbin/bagel-7b-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": 4096,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.37.0.dev0",
28
+ "use_cache": false,
29
+ "vocab_size": 32000
30
+ }
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a616a923925252fd01932df6058ca5a937756af137bbb5868d920345d7c39a
3
+ size 9919813624
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89defad130631734832dcce5d3ad65f03a4fc049107c4d7ccde385dfd45afae7
3
+ size 9982454720
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd14e4f5a83b3eaf71431780e092abf82010c4cb90a36604d89c5ffec36f1ef8
3
+ size 9982454720
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce4185aec54108a9acb9e59df9f3cd76a2aad524b95473af48478724092b9b5
3
+ size 9982454640
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ac6502b641bb1fba87da6ab8c849813417f450e4ca2c5f1e68ea360508fe71
3
+ size 9982454712
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad98dc788fd5f0cb71bee39c303273a48fc2c33a1d64eade7c2e623739a4060a
3
+ size 9982454712
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4102b0c9319e281bbdafe5ba34dcd4d454d98f81b890542bc810a01906e709e2
3
+ size 9982454640
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fdaa8bc758b0a00491423dce5f5df8d78578ca93c37d1406256f4ff170716e
3
+ size 9982454712
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edd3c20337ac5f004667219496e08a8b5be6471c5e31a3277196888fbf2fb35
3
+ size 9982454712
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278f2e973fcc2d40c0e932ceaf539d524abf9bcc26c3e4dcc66f72385fe7706e
3
+ size 3626261624
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.norm.weight": "model-00001-of-00010.safetensors", "lm_head.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00010.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00010.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00010.safetensors", "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}\n"
44
+ }