Alsebay commited on
Commit
f7f71f8
1 Parent(s): e3c0ee4
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Nitral-AI/KukulStanta-7B",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
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": 3,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 3,
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": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.3",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14affd7d4a8044ff366d2311c008386f0c1c6b871ca7d49f7afcdbb70e037268
3
+ size 1933849936
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352e0671c502a2d5dd9f03545b2a5051d1815baff0e7859ed753470a3af5670d
3
+ size 1996490952
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd68da44afb6892e0f04a060f806985d39d5f32c0964f382fa83954e122a646
3
+ size 1996490968
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3802d8f987fe2f5bdb72fcb157acece17f5c64fca97eaf1bd370b147919da2
3
+ size 1996490968
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00fbea769464b7aa893b76c99cdfc5526d9e63cba585727bc5d2586a69cd0e39
3
+ size 1996490968
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d762d76224a5fe316fd8020a2d439807314506dfad079b96792ad5776e53d9
3
+ size 1996490968
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff35e1e529fd94dfe0c421e1bbaa6b299a23016a52ae6443b3e7214c48ef20b3
3
+ size 1996490952
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d94b44d1db200dd0b3f7f2a4fc1537e997508e3b579708ae2dde6896db574e
3
+ size 1996490952
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0058faf8eac1c50f88c5bff57a6105ac047a7b8000e8f7d274928ab07ae8d90
3
+ size 1996490968
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6f09b6e8be894d9180580bf9e002b435948cdd9a10aa34ca36e1d287e4901f
3
+ size 1996490968
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591baf3a246dcfc09a1f80124e5c8f2ab4111a9d76dfb1ca3686f57708b60cae
3
+ size 1996490968
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383005c7d637b1f9c0e5dba8e15917d2f3bf811206ba7e6765b712731834d04a
3
+ size 1996490960
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84db36e4c42c17286ec7a6cd7507f428dafab22abdf23351aac68096b58f4394
3
+ size 1996490952
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1f6e2d9bab4e3556cc1d4b8622afed1d8d357daee1d15012fcc4c6999789bd
3
+ size 1996490960
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401ebc2973391060f9725f4c0deb13718044250697b11c58fc7a2d6c36fde4a0
3
+ size 1996490968
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f530cf869d522f61715be8a4e20f0fd5158d8e8c70d1daeb4bf6094e21e2f7d1
3
+ size 1996490968
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd1e218b9a0c5de267cbb7c6b1ec91ad64762abe85938ed89c8f1595b05621e
3
+ size 1996490968
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222ef9f5ea80eed7119182775fd199a90063f8360f67681f27ee384763a09ccf
3
+ size 1996765216
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2168bfae34491dadb42b36bf821c8a357c212aec5182138dc74e321ee4e6cba
3
+ size 1158423000
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.norm.weight": "model-00001-of-00019.safetensors", "lm_head.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.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": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }