TroyDoesAI commited on
Commit
d29fb74
·
verified ·
1 Parent(s): eb9a601

Mini-BlackSheep

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TroyDoesAI/BlackSheep-MoE",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 4,
21
+ "output_router_logits": false,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.48.3",
30
+ "use_cache": true,
31
+ "vocab_size": 131072
32
+ }
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95bd305aad72b13c3e25b97c91c19519173d6208d8061624475bc2db1dc65aa
3
+ size 4991286216
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1dae8e409b637a546f018e529857cbd152c8953cd73bb264c737d64123a468e
3
+ size 4907464440
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f51b88d00207f204a67df56fd3a3fd8dd8263e9e5c1f02581d471963e67335d
3
+ size 4865583536
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82440ab0076cde2535770ab754fefa29d91f4241d7929359a35518f7e3859533
3
+ size 4865583536
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcc778620f2fb299860959b499f3e6bd051d0d64cde15e92e46bb6ad958c64a
3
+ size 4907464456
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec8d65e54c78bd21e9ad9f0c4413f69656a037ca033c2bb7cbdf623350f7230
3
+ size 4865583520
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b7488b8de2c13b7171daab829ac825d7f92e10c148a7b88fe7855b140e0038
3
+ size 4959955288
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d173f3c96d7f9ca47863f7352079e7daa2f6d20813e70898d37e3a8b10153b
3
+ size 4959893488
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f729c2c411b81ffb01c82272be49cf19b461d75d1b429f1491c0b514ad9c6738
3
+ size 4865583536
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b46b198cd63464a75e642565d45d4ef4a1b48b71cd02696514c5f1325970a72
3
+ size 4907464440
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce1f88f740a19b9835940065f2a0db91991fac64778378f13ce4ffc8b8230a
3
+ size 4865583536
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0187df9f3d796f085c7f747b95bc6b814ecbe85885c83b3c615d7729ae6deb7a
3
+ size 4865583536
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345ff786b291d33d8d30043214370b42056db5a0807440afb8837fc88bab88fa
3
+ size 4907464456
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0ba1f9bcb1174802dbdb38541eceb332c4433c67d982dfa0edf65f01b70cdd
3
+ size 4865583512
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823dad3792a9ab28ffa729bee922659326b987a70025f44cd43c65c1d3812289
3
+ size 4959955232
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ae73389341b8277593082bc1132b27fef4463b544d7782723be723de98e6eb
3
+ size 3785497600
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00003-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00010-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00011-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00011-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00012-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00012-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00012-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00013-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00013-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00014-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00014-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00014-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00015-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00015-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00015-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a046b64b5eda8178d73f3a3b5c9ff1278e6c55b2ff2628dc20bee39b3371ab7
3
+ size 17078444
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff