Crystalcareai commited on
Commit
d678a70
1 Parent(s): 29fe906

Upload folder using huggingface_hub

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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Crystalcareai/GemMoE-Beta",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_experts_per_tok": 2,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 16,
21
+ "num_local_experts": 8,
22
+ "output_router_logits": false,
23
+ "pad_token_id": 0,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.38.2",
31
+ "use_cache": false,
32
+ "vocab_size": 256000
33
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "do_sample": true,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.38.2"
8
+ }
pytorch_model-00001-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe619042db418828e414d53c449ed3fa73c1ef469303774532cf4db2f37fcebd
3
+ size 4995475862
pytorch_model-00002-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a059458d6b0aed6bd258cbd2dc3660886b7a8d16cbf1ca27588f7fc7c108c7f5
3
+ size 4982922912
pytorch_model-00003-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3ed441cedf660403a48936b304b08fb2957bd7a5749eda928a626a7f84e5e7
3
+ size 4982959290
pytorch_model-00004-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc48bf0b2b528739f00f8ef7af158a7e74a31af80674a1f8b273c22f27d2354
3
+ size 4932577464
pytorch_model-00005-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d4441caab9e2733e6220d881b49b96c5035cbdf16099c1932037bbd1ea3140
3
+ size 4932577464
pytorch_model-00006-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f3bb146adb83f21b10266d80d473433215eb10761fc96a3f0c237978ecf244
3
+ size 4932577464
pytorch_model-00007-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029a656af03a5785efd7399840ff942bc750ebf980333d7b780cc81e346ee1fd
3
+ size 4932577500
pytorch_model-00008-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ba1441583ab91800a5e26838426584dd835e81f736e73ff9a9a8db47dfeb60
3
+ size 4882259882
pytorch_model-00009-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6404744577e49a93fcef8f0b1f0d75f24fd235de5080005e335a551bfbc86d8e
3
+ size 4932626954
pytorch_model-00010-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bb4223d2239ef8cee60236a1e86410b89d916390d128a7a41035c6d98fba89
3
+ size 4932577528
pytorch_model-00011-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8fdb6ccb0f9652053a0a3ae916dbb6e4afb8cfdff679835673c2d8f2ebdb81
3
+ size 4932577528
pytorch_model-00012-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80965c534885cdafb6fd9b97352da7d71f8810b79dc6bbdc8fc441497b997e95
3
+ size 4932577528
pytorch_model-00013-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aaf40d38771279866cd9b482ed381eea82fba204d193b4cd0c0068599c0d4cd
3
+ size 4982922976
pytorch_model-00014-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58aeada8a5bb2d91a3725b7755231b65ddcf89ba71477c0b7e6c5e7f5e03c5f
3
+ size 4982959354
pytorch_model-00015-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ab7afed2af77fba598a697869aee3aad7274e751bfde0576c9cf61f83a9714
3
+ size 4932577528
pytorch_model-00016-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2efc12d0ae9a9e203fe9c026c095b3b2fc1787be3109a5fe86506ac0854fe1ac
3
+ size 4932577528
pytorch_model-00017-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfb70ca36d2fa15f9473f6f8b4018ce812924748de158409cb7bd9b2e952c40a
3
+ size 4932577528
pytorch_model-00018-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b5bce795e5923105dac36666ea92d0bcf24e5da5111a7172a4e3d48374b0d1
3
+ size 4932577564
pytorch_model-00019-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a8cd85b6465de9042a29a0bf1ba0c0e4ba2c2f3183776dba5e817597f237b1
3
+ size 4882259882
pytorch_model-00020-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fa2528417945c3864e047bd41f0941d0442461eb992f4dc89cbb9dfcb5678c
3
+ size 4932627018
pytorch_model-00021-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017b6458a160c25099f7a356029ea9bfbca62af54c1039cb535798af6b13b78c
3
+ size 4932577528
pytorch_model-00022-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718fba3e3c0e5b3836db1dcdebd6867b72f487a5c4d42e26e79d18ee6465f3bf
3
+ size 4932577528
pytorch_model-00023-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dff502b54989059c3c46879d7ea2db4dd7b9b2c3ef24743dd9198723baca1da
3
+ size 4932577528
pytorch_model-00024-of-00024.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed1ba303191dbd1249c9da97120d81754f1511c634ba705a49889bb5c49e424
3
+ size 4932597058
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,962 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 118545340416
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00024.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00024.bin",
8
+ "model.layers.0.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00001-of-00024.bin",
9
+ "model.layers.0.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00001-of-00024.bin",
10
+ "model.layers.0.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00001-of-00024.bin",
11
+ "model.layers.0.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00001-of-00024.bin",
12
+ "model.layers.0.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00001-of-00024.bin",
13
+ "model.layers.0.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00001-of-00024.bin",
14
+ "model.layers.0.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00001-of-00024.bin",
15
+ "model.layers.0.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00001-of-00024.bin",
16
+ "model.layers.0.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00001-of-00024.bin",
17
+ "model.layers.0.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00001-of-00024.bin",
18
+ "model.layers.0.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00001-of-00024.bin",
19
+ "model.layers.0.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00001-of-00024.bin",
20
+ "model.layers.0.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00001-of-00024.bin",
21
+ "model.layers.0.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00001-of-00024.bin",
22
+ "model.layers.0.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00001-of-00024.bin",
23
+ "model.layers.0.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00001-of-00024.bin",
24
+ "model.layers.0.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00001-of-00024.bin",
25
+ "model.layers.0.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00001-of-00024.bin",
26
+ "model.layers.0.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00001-of-00024.bin",
27
+ "model.layers.0.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00024.bin",
28
+ "model.layers.0.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00024.bin",
29
+ "model.layers.0.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00024.bin",
30
+ "model.layers.0.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00024.bin",
31
+ "model.layers.0.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00024.bin",
32
+ "model.layers.0.block_sparse_moe.gate.weight": "pytorch_model-00001-of-00024.bin",
33
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00024.bin",
34
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00024.bin",
35
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00024.bin",
36
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00024.bin",
37
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00024.bin",
38
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00024.bin",
39
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00024.bin",
40
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00024.bin",
41
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00024.bin",
42
+ "model.layers.1.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00002-of-00024.bin",
43
+ "model.layers.1.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00002-of-00024.bin",
44
+ "model.layers.1.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00002-of-00024.bin",
45
+ "model.layers.1.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00002-of-00024.bin",
46
+ "model.layers.1.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00002-of-00024.bin",
47
+ "model.layers.1.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00002-of-00024.bin",
48
+ "model.layers.1.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00002-of-00024.bin",
49
+ "model.layers.1.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00002-of-00024.bin",
50
+ "model.layers.1.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00002-of-00024.bin",
51
+ "model.layers.1.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00002-of-00024.bin",
52
+ "model.layers.1.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00002-of-00024.bin",
53
+ "model.layers.1.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00002-of-00024.bin",
54
+ "model.layers.1.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00002-of-00024.bin",
55
+ "model.layers.1.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00002-of-00024.bin",
56
+ "model.layers.1.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00002-of-00024.bin",
57
+ "model.layers.1.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00002-of-00024.bin",
58
+ "model.layers.1.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00002-of-00024.bin",
59
+ "model.layers.1.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00002-of-00024.bin",
60
+ "model.layers.1.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00002-of-00024.bin",
61
+ "model.layers.1.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00002-of-00024.bin",
62
+ "model.layers.1.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00002-of-00024.bin",
63
+ "model.layers.1.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00002-of-00024.bin",
64
+ "model.layers.1.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00002-of-00024.bin",
65
+ "model.layers.1.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00002-of-00024.bin",
66
+ "model.layers.1.block_sparse_moe.gate.weight": "pytorch_model-00002-of-00024.bin",
67
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00024.bin",
68
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00024.bin",
69
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00024.bin",
70
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00024.bin",
71
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00024.bin",
72
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00024.bin",
73
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00024.bin",
74
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00024.bin",
75
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00024.bin",
76
+ "model.layers.10.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00024.bin",
77
+ "model.layers.10.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00024.bin",
78
+ "model.layers.10.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00024.bin",
79
+ "model.layers.10.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00024.bin",
80
+ "model.layers.10.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00024.bin",
81
+ "model.layers.10.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00024.bin",
82
+ "model.layers.10.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00024.bin",
83
+ "model.layers.10.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00024.bin",
84
+ "model.layers.10.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00024.bin",
85
+ "model.layers.10.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00010-of-00024.bin",
86
+ "model.layers.10.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00010-of-00024.bin",
87
+ "model.layers.10.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00010-of-00024.bin",
88
+ "model.layers.10.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00010-of-00024.bin",
89
+ "model.layers.10.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00010-of-00024.bin",
90
+ "model.layers.10.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00010-of-00024.bin",
91
+ "model.layers.10.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00010-of-00024.bin",
92
+ "model.layers.10.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00010-of-00024.bin",
93
+ "model.layers.10.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00010-of-00024.bin",
94
+ "model.layers.10.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00010-of-00024.bin",
95
+ "model.layers.10.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00010-of-00024.bin",
96
+ "model.layers.10.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00010-of-00024.bin",
97
+ "model.layers.10.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00010-of-00024.bin",
98
+ "model.layers.10.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00010-of-00024.bin",
99
+ "model.layers.10.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00010-of-00024.bin",
100
+ "model.layers.10.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00024.bin",
101
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00010-of-00024.bin",
102
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00009-of-00024.bin",
103
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00009-of-00024.bin",
104
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00009-of-00024.bin",
105
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00010-of-00024.bin",
106
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00009-of-00024.bin",
107
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00009-of-00024.bin",
108
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00009-of-00024.bin",
109
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00009-of-00024.bin",
110
+ "model.layers.11.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00010-of-00024.bin",
111
+ "model.layers.11.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00010-of-00024.bin",
112
+ "model.layers.11.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00010-of-00024.bin",
113
+ "model.layers.11.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00010-of-00024.bin",
114
+ "model.layers.11.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00010-of-00024.bin",
115
+ "model.layers.11.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00010-of-00024.bin",
116
+ "model.layers.11.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00010-of-00024.bin",
117
+ "model.layers.11.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00010-of-00024.bin",
118
+ "model.layers.11.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00010-of-00024.bin",
119
+ "model.layers.11.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00024.bin",
120
+ "model.layers.11.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00024.bin",
121
+ "model.layers.11.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00024.bin",
122
+ "model.layers.11.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00024.bin",
123
+ "model.layers.11.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00024.bin",
124
+ "model.layers.11.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00011-of-00024.bin",
125
+ "model.layers.11.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00011-of-00024.bin",
126
+ "model.layers.11.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00011-of-00024.bin",
127
+ "model.layers.11.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00011-of-00024.bin",
128
+ "model.layers.11.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00011-of-00024.bin",
129
+ "model.layers.11.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00011-of-00024.bin",
130
+ "model.layers.11.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00011-of-00024.bin",
131
+ "model.layers.11.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00011-of-00024.bin",
132
+ "model.layers.11.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00011-of-00024.bin",
133
+ "model.layers.11.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00011-of-00024.bin",
134
+ "model.layers.11.block_sparse_moe.gate.weight": "pytorch_model-00010-of-00024.bin",
135
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00011-of-00024.bin",
136
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00010-of-00024.bin",
137
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00010-of-00024.bin",
138
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00010-of-00024.bin",
139
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00011-of-00024.bin",
140
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00010-of-00024.bin",
141
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00010-of-00024.bin",
142
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00010-of-00024.bin",
143
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00010-of-00024.bin",
144
+ "model.layers.12.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00011-of-00024.bin",
145
+ "model.layers.12.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00011-of-00024.bin",
146
+ "model.layers.12.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00011-of-00024.bin",
147
+ "model.layers.12.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00011-of-00024.bin",
148
+ "model.layers.12.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00011-of-00024.bin",
149
+ "model.layers.12.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00011-of-00024.bin",
150
+ "model.layers.12.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00011-of-00024.bin",
151
+ "model.layers.12.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00011-of-00024.bin",
152
+ "model.layers.12.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00011-of-00024.bin",
153
+ "model.layers.12.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00011-of-00024.bin",
154
+ "model.layers.12.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00011-of-00024.bin",
155
+ "model.layers.12.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00011-of-00024.bin",
156
+ "model.layers.12.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00011-of-00024.bin",
157
+ "model.layers.12.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00011-of-00024.bin",
158
+ "model.layers.12.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00024.bin",
159
+ "model.layers.12.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00024.bin",
160
+ "model.layers.12.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00024.bin",
161
+ "model.layers.12.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00024.bin",
162
+ "model.layers.12.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00024.bin",
163
+ "model.layers.12.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00012-of-00024.bin",
164
+ "model.layers.12.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00012-of-00024.bin",
165
+ "model.layers.12.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00012-of-00024.bin",
166
+ "model.layers.12.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00012-of-00024.bin",
167
+ "model.layers.12.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00012-of-00024.bin",
168
+ "model.layers.12.block_sparse_moe.gate.weight": "pytorch_model-00011-of-00024.bin",
169
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00012-of-00024.bin",
170
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00011-of-00024.bin",
171
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00011-of-00024.bin",
172
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00011-of-00024.bin",
173
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00012-of-00024.bin",
174
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00011-of-00024.bin",
175
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00011-of-00024.bin",
176
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00011-of-00024.bin",
177
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00011-of-00024.bin",
178
+ "model.layers.13.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00012-of-00024.bin",
179
+ "model.layers.13.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00012-of-00024.bin",
180
+ "model.layers.13.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00012-of-00024.bin",
181
+ "model.layers.13.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00012-of-00024.bin",
182
+ "model.layers.13.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00012-of-00024.bin",
183
+ "model.layers.13.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00012-of-00024.bin",
184
+ "model.layers.13.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00012-of-00024.bin",
185
+ "model.layers.13.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00012-of-00024.bin",
186
+ "model.layers.13.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00012-of-00024.bin",
187
+ "model.layers.13.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00012-of-00024.bin",
188
+ "model.layers.13.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00012-of-00024.bin",
189
+ "model.layers.13.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00012-of-00024.bin",
190
+ "model.layers.13.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00012-of-00024.bin",
191
+ "model.layers.13.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00012-of-00024.bin",
192
+ "model.layers.13.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00012-of-00024.bin",
193
+ "model.layers.13.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00012-of-00024.bin",
194
+ "model.layers.13.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00012-of-00024.bin",
195
+ "model.layers.13.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00012-of-00024.bin",
196
+ "model.layers.13.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00012-of-00024.bin",
197
+ "model.layers.13.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00024.bin",
198
+ "model.layers.13.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00024.bin",
199
+ "model.layers.13.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00024.bin",
200
+ "model.layers.13.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00024.bin",
201
+ "model.layers.13.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00024.bin",
202
+ "model.layers.13.block_sparse_moe.gate.weight": "pytorch_model-00012-of-00024.bin",
203
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00013-of-00024.bin",
204
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00012-of-00024.bin",
205
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00012-of-00024.bin",
206
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00012-of-00024.bin",
207
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00013-of-00024.bin",
208
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00012-of-00024.bin",
209
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00012-of-00024.bin",
210
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00012-of-00024.bin",
211
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00012-of-00024.bin",
212
+ "model.layers.14.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00013-of-00024.bin",
213
+ "model.layers.14.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00013-of-00024.bin",
214
+ "model.layers.14.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00013-of-00024.bin",
215
+ "model.layers.14.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00013-of-00024.bin",
216
+ "model.layers.14.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00013-of-00024.bin",
217
+ "model.layers.14.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00013-of-00024.bin",
218
+ "model.layers.14.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00013-of-00024.bin",
219
+ "model.layers.14.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00013-of-00024.bin",
220
+ "model.layers.14.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00013-of-00024.bin",
221
+ "model.layers.14.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00013-of-00024.bin",
222
+ "model.layers.14.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00013-of-00024.bin",
223
+ "model.layers.14.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00013-of-00024.bin",
224
+ "model.layers.14.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00013-of-00024.bin",
225
+ "model.layers.14.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00013-of-00024.bin",
226
+ "model.layers.14.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00013-of-00024.bin",
227
+ "model.layers.14.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00013-of-00024.bin",
228
+ "model.layers.14.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00013-of-00024.bin",
229
+ "model.layers.14.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00013-of-00024.bin",
230
+ "model.layers.14.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00013-of-00024.bin",
231
+ "model.layers.14.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00013-of-00024.bin",
232
+ "model.layers.14.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00013-of-00024.bin",
233
+ "model.layers.14.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00013-of-00024.bin",
234
+ "model.layers.14.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00013-of-00024.bin",
235
+ "model.layers.14.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00013-of-00024.bin",
236
+ "model.layers.14.block_sparse_moe.gate.weight": "pytorch_model-00013-of-00024.bin",
237
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00013-of-00024.bin",
238
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00013-of-00024.bin",
239
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00013-of-00024.bin",
240
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00013-of-00024.bin",
241
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00013-of-00024.bin",
242
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00013-of-00024.bin",
243
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00013-of-00024.bin",
244
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00013-of-00024.bin",
245
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00013-of-00024.bin",
246
+ "model.layers.15.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00024.bin",
247
+ "model.layers.15.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00024.bin",
248
+ "model.layers.15.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00014-of-00024.bin",
249
+ "model.layers.15.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00014-of-00024.bin",
250
+ "model.layers.15.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00014-of-00024.bin",
251
+ "model.layers.15.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00014-of-00024.bin",
252
+ "model.layers.15.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00014-of-00024.bin",
253
+ "model.layers.15.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00014-of-00024.bin",
254
+ "model.layers.15.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00014-of-00024.bin",
255
+ "model.layers.15.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00014-of-00024.bin",
256
+ "model.layers.15.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00014-of-00024.bin",
257
+ "model.layers.15.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00014-of-00024.bin",
258
+ "model.layers.15.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00014-of-00024.bin",
259
+ "model.layers.15.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00014-of-00024.bin",
260
+ "model.layers.15.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00014-of-00024.bin",
261
+ "model.layers.15.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00014-of-00024.bin",
262
+ "model.layers.15.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00014-of-00024.bin",
263
+ "model.layers.15.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00014-of-00024.bin",
264
+ "model.layers.15.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00014-of-00024.bin",
265
+ "model.layers.15.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00014-of-00024.bin",
266
+ "model.layers.15.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00014-of-00024.bin",
267
+ "model.layers.15.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00014-of-00024.bin",
268
+ "model.layers.15.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00014-of-00024.bin",
269
+ "model.layers.15.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00014-of-00024.bin",
270
+ "model.layers.15.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00024.bin",
271
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00014-of-00024.bin",
272
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00014-of-00024.bin",
273
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00014-of-00024.bin",
274
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00014-of-00024.bin",
275
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00014-of-00024.bin",
276
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00013-of-00024.bin",
277
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00014-of-00024.bin",
278
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00013-of-00024.bin",
279
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00014-of-00024.bin",
280
+ "model.layers.16.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00014-of-00024.bin",
281
+ "model.layers.16.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00014-of-00024.bin",
282
+ "model.layers.16.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00024.bin",
283
+ "model.layers.16.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00024.bin",
284
+ "model.layers.16.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00024.bin",
285
+ "model.layers.16.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00024.bin",
286
+ "model.layers.16.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00024.bin",
287
+ "model.layers.16.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00015-of-00024.bin",
288
+ "model.layers.16.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00015-of-00024.bin",
289
+ "model.layers.16.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00015-of-00024.bin",
290
+ "model.layers.16.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00015-of-00024.bin",
291
+ "model.layers.16.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00015-of-00024.bin",
292
+ "model.layers.16.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00015-of-00024.bin",
293
+ "model.layers.16.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00015-of-00024.bin",
294
+ "model.layers.16.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00015-of-00024.bin",
295
+ "model.layers.16.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00015-of-00024.bin",
296
+ "model.layers.16.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00015-of-00024.bin",
297
+ "model.layers.16.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00015-of-00024.bin",
298
+ "model.layers.16.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00015-of-00024.bin",
299
+ "model.layers.16.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00015-of-00024.bin",
300
+ "model.layers.16.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00015-of-00024.bin",
301
+ "model.layers.16.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00015-of-00024.bin",
302
+ "model.layers.16.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00015-of-00024.bin",
303
+ "model.layers.16.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00015-of-00024.bin",
304
+ "model.layers.16.block_sparse_moe.gate.weight": "pytorch_model-00014-of-00024.bin",
305
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00015-of-00024.bin",
306
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00014-of-00024.bin",
307
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00014-of-00024.bin",
308
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00014-of-00024.bin",
309
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00015-of-00024.bin",
310
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00014-of-00024.bin",
311
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00014-of-00024.bin",
312
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00014-of-00024.bin",
313
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00014-of-00024.bin",
314
+ "model.layers.17.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00015-of-00024.bin",
315
+ "model.layers.17.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00015-of-00024.bin",
316
+ "model.layers.17.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00015-of-00024.bin",
317
+ "model.layers.17.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00015-of-00024.bin",
318
+ "model.layers.17.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00015-of-00024.bin",
319
+ "model.layers.17.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00015-of-00024.bin",
320
+ "model.layers.17.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00015-of-00024.bin",
321
+ "model.layers.17.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00024.bin",
322
+ "model.layers.17.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00024.bin",
323
+ "model.layers.17.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00024.bin",
324
+ "model.layers.17.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00024.bin",
325
+ "model.layers.17.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00024.bin",
326
+ "model.layers.17.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00016-of-00024.bin",
327
+ "model.layers.17.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00016-of-00024.bin",
328
+ "model.layers.17.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00016-of-00024.bin",
329
+ "model.layers.17.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00016-of-00024.bin",
330
+ "model.layers.17.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00016-of-00024.bin",
331
+ "model.layers.17.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00016-of-00024.bin",
332
+ "model.layers.17.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00016-of-00024.bin",
333
+ "model.layers.17.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00016-of-00024.bin",
334
+ "model.layers.17.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00016-of-00024.bin",
335
+ "model.layers.17.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00016-of-00024.bin",
336
+ "model.layers.17.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00016-of-00024.bin",
337
+ "model.layers.17.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00016-of-00024.bin",
338
+ "model.layers.17.block_sparse_moe.gate.weight": "pytorch_model-00015-of-00024.bin",
339
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00016-of-00024.bin",
340
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00015-of-00024.bin",
341
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00015-of-00024.bin",
342
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00015-of-00024.bin",
343
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00016-of-00024.bin",
344
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00015-of-00024.bin",
345
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00015-of-00024.bin",
346
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00015-of-00024.bin",
347
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00015-of-00024.bin",
348
+ "model.layers.18.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00016-of-00024.bin",
349
+ "model.layers.18.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00016-of-00024.bin",
350
+ "model.layers.18.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00016-of-00024.bin",
351
+ "model.layers.18.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00016-of-00024.bin",
352
+ "model.layers.18.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00016-of-00024.bin",
353
+ "model.layers.18.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00016-of-00024.bin",
354
+ "model.layers.18.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00016-of-00024.bin",
355
+ "model.layers.18.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00016-of-00024.bin",
356
+ "model.layers.18.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00016-of-00024.bin",
357
+ "model.layers.18.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00016-of-00024.bin",
358
+ "model.layers.18.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00016-of-00024.bin",
359
+ "model.layers.18.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00016-of-00024.bin",
360
+ "model.layers.18.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00024.bin",
361
+ "model.layers.18.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00024.bin",
362
+ "model.layers.18.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00024.bin",
363
+ "model.layers.18.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00024.bin",
364
+ "model.layers.18.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00024.bin",
365
+ "model.layers.18.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00017-of-00024.bin",
366
+ "model.layers.18.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00017-of-00024.bin",
367
+ "model.layers.18.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00017-of-00024.bin",
368
+ "model.layers.18.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00017-of-00024.bin",
369
+ "model.layers.18.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00017-of-00024.bin",
370
+ "model.layers.18.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00017-of-00024.bin",
371
+ "model.layers.18.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00017-of-00024.bin",
372
+ "model.layers.18.block_sparse_moe.gate.weight": "pytorch_model-00016-of-00024.bin",
373
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00017-of-00024.bin",
374
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00016-of-00024.bin",
375
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00016-of-00024.bin",
376
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00016-of-00024.bin",
377
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00017-of-00024.bin",
378
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00016-of-00024.bin",
379
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00016-of-00024.bin",
380
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00016-of-00024.bin",
381
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00016-of-00024.bin",
382
+ "model.layers.19.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00017-of-00024.bin",
383
+ "model.layers.19.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00017-of-00024.bin",
384
+ "model.layers.19.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00017-of-00024.bin",
385
+ "model.layers.19.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00017-of-00024.bin",
386
+ "model.layers.19.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00017-of-00024.bin",
387
+ "model.layers.19.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00017-of-00024.bin",
388
+ "model.layers.19.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00017-of-00024.bin",
389
+ "model.layers.19.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00017-of-00024.bin",
390
+ "model.layers.19.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00017-of-00024.bin",
391
+ "model.layers.19.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00017-of-00024.bin",
392
+ "model.layers.19.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00017-of-00024.bin",
393
+ "model.layers.19.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00017-of-00024.bin",
394
+ "model.layers.19.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00017-of-00024.bin",
395
+ "model.layers.19.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00017-of-00024.bin",
396
+ "model.layers.19.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00017-of-00024.bin",
397
+ "model.layers.19.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00017-of-00024.bin",
398
+ "model.layers.19.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00017-of-00024.bin",
399
+ "model.layers.19.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00024.bin",
400
+ "model.layers.19.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00024.bin",
401
+ "model.layers.19.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00024.bin",
402
+ "model.layers.19.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00024.bin",
403
+ "model.layers.19.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00024.bin",
404
+ "model.layers.19.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00018-of-00024.bin",
405
+ "model.layers.19.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00018-of-00024.bin",
406
+ "model.layers.19.block_sparse_moe.gate.weight": "pytorch_model-00017-of-00024.bin",
407
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00018-of-00024.bin",
408
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00017-of-00024.bin",
409
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00017-of-00024.bin",
410
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00017-of-00024.bin",
411
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00018-of-00024.bin",
412
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00017-of-00024.bin",
413
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00017-of-00024.bin",
414
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00017-of-00024.bin",
415
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00017-of-00024.bin",
416
+ "model.layers.2.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00024.bin",
417
+ "model.layers.2.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00024.bin",
418
+ "model.layers.2.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00003-of-00024.bin",
419
+ "model.layers.2.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00003-of-00024.bin",
420
+ "model.layers.2.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00003-of-00024.bin",
421
+ "model.layers.2.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00003-of-00024.bin",
422
+ "model.layers.2.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00003-of-00024.bin",
423
+ "model.layers.2.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00003-of-00024.bin",
424
+ "model.layers.2.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00003-of-00024.bin",
425
+ "model.layers.2.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00003-of-00024.bin",
426
+ "model.layers.2.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00003-of-00024.bin",
427
+ "model.layers.2.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00003-of-00024.bin",
428
+ "model.layers.2.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00003-of-00024.bin",
429
+ "model.layers.2.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00003-of-00024.bin",
430
+ "model.layers.2.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00003-of-00024.bin",
431
+ "model.layers.2.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00003-of-00024.bin",
432
+ "model.layers.2.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00003-of-00024.bin",
433
+ "model.layers.2.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00003-of-00024.bin",
434
+ "model.layers.2.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00003-of-00024.bin",
435
+ "model.layers.2.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00003-of-00024.bin",
436
+ "model.layers.2.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00003-of-00024.bin",
437
+ "model.layers.2.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00003-of-00024.bin",
438
+ "model.layers.2.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00003-of-00024.bin",
439
+ "model.layers.2.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00003-of-00024.bin",
440
+ "model.layers.2.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00024.bin",
441
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00024.bin",
442
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00024.bin",
443
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00024.bin",
444
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00024.bin",
445
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00024.bin",
446
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00024.bin",
447
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00024.bin",
448
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00024.bin",
449
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00024.bin",
450
+ "model.layers.20.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00018-of-00024.bin",
451
+ "model.layers.20.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00018-of-00024.bin",
452
+ "model.layers.20.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00018-of-00024.bin",
453
+ "model.layers.20.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00018-of-00024.bin",
454
+ "model.layers.20.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00018-of-00024.bin",
455
+ "model.layers.20.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00018-of-00024.bin",
456
+ "model.layers.20.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00018-of-00024.bin",
457
+ "model.layers.20.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00018-of-00024.bin",
458
+ "model.layers.20.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00018-of-00024.bin",
459
+ "model.layers.20.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00018-of-00024.bin",
460
+ "model.layers.20.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00018-of-00024.bin",
461
+ "model.layers.20.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00018-of-00024.bin",
462
+ "model.layers.20.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00018-of-00024.bin",
463
+ "model.layers.20.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00018-of-00024.bin",
464
+ "model.layers.20.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00018-of-00024.bin",
465
+ "model.layers.20.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00018-of-00024.bin",
466
+ "model.layers.20.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00018-of-00024.bin",
467
+ "model.layers.20.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00018-of-00024.bin",
468
+ "model.layers.20.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00018-of-00024.bin",
469
+ "model.layers.20.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00018-of-00024.bin",
470
+ "model.layers.20.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00018-of-00024.bin",
471
+ "model.layers.20.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00018-of-00024.bin",
472
+ "model.layers.20.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00024.bin",
473
+ "model.layers.20.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00024.bin",
474
+ "model.layers.20.block_sparse_moe.gate.weight": "pytorch_model-00018-of-00024.bin",
475
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00019-of-00024.bin",
476
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00018-of-00024.bin",
477
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00018-of-00024.bin",
478
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00018-of-00024.bin",
479
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00019-of-00024.bin",
480
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00018-of-00024.bin",
481
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00018-of-00024.bin",
482
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00018-of-00024.bin",
483
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00018-of-00024.bin",
484
+ "model.layers.21.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00019-of-00024.bin",
485
+ "model.layers.21.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00019-of-00024.bin",
486
+ "model.layers.21.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00019-of-00024.bin",
487
+ "model.layers.21.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00019-of-00024.bin",
488
+ "model.layers.21.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00019-of-00024.bin",
489
+ "model.layers.21.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00019-of-00024.bin",
490
+ "model.layers.21.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00019-of-00024.bin",
491
+ "model.layers.21.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00019-of-00024.bin",
492
+ "model.layers.21.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00019-of-00024.bin",
493
+ "model.layers.21.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00019-of-00024.bin",
494
+ "model.layers.21.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00019-of-00024.bin",
495
+ "model.layers.21.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00019-of-00024.bin",
496
+ "model.layers.21.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00019-of-00024.bin",
497
+ "model.layers.21.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00019-of-00024.bin",
498
+ "model.layers.21.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00019-of-00024.bin",
499
+ "model.layers.21.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00019-of-00024.bin",
500
+ "model.layers.21.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00019-of-00024.bin",
501
+ "model.layers.21.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00019-of-00024.bin",
502
+ "model.layers.21.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00019-of-00024.bin",
503
+ "model.layers.21.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00019-of-00024.bin",
504
+ "model.layers.21.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00019-of-00024.bin",
505
+ "model.layers.21.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00019-of-00024.bin",
506
+ "model.layers.21.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00019-of-00024.bin",
507
+ "model.layers.21.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00019-of-00024.bin",
508
+ "model.layers.21.block_sparse_moe.gate.weight": "pytorch_model-00019-of-00024.bin",
509
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00019-of-00024.bin",
510
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00019-of-00024.bin",
511
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00019-of-00024.bin",
512
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00019-of-00024.bin",
513
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00019-of-00024.bin",
514
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00019-of-00024.bin",
515
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00019-of-00024.bin",
516
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00019-of-00024.bin",
517
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00019-of-00024.bin",
518
+ "model.layers.22.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00020-of-00024.bin",
519
+ "model.layers.22.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00020-of-00024.bin",
520
+ "model.layers.22.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00020-of-00024.bin",
521
+ "model.layers.22.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00020-of-00024.bin",
522
+ "model.layers.22.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00020-of-00024.bin",
523
+ "model.layers.22.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00020-of-00024.bin",
524
+ "model.layers.22.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00020-of-00024.bin",
525
+ "model.layers.22.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00020-of-00024.bin",
526
+ "model.layers.22.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00020-of-00024.bin",
527
+ "model.layers.22.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00020-of-00024.bin",
528
+ "model.layers.22.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00020-of-00024.bin",
529
+ "model.layers.22.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00020-of-00024.bin",
530
+ "model.layers.22.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00020-of-00024.bin",
531
+ "model.layers.22.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00020-of-00024.bin",
532
+ "model.layers.22.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00020-of-00024.bin",
533
+ "model.layers.22.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00020-of-00024.bin",
534
+ "model.layers.22.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00020-of-00024.bin",
535
+ "model.layers.22.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00020-of-00024.bin",
536
+ "model.layers.22.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00020-of-00024.bin",
537
+ "model.layers.22.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00020-of-00024.bin",
538
+ "model.layers.22.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00020-of-00024.bin",
539
+ "model.layers.22.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00020-of-00024.bin",
540
+ "model.layers.22.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00020-of-00024.bin",
541
+ "model.layers.22.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00020-of-00024.bin",
542
+ "model.layers.22.block_sparse_moe.gate.weight": "pytorch_model-00020-of-00024.bin",
543
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00020-of-00024.bin",
544
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00020-of-00024.bin",
545
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00019-of-00024.bin",
546
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00019-of-00024.bin",
547
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00020-of-00024.bin",
548
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00019-of-00024.bin",
549
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00019-of-00024.bin",
550
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00019-of-00024.bin",
551
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00019-of-00024.bin",
552
+ "model.layers.23.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00020-of-00024.bin",
553
+ "model.layers.23.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00020-of-00024.bin",
554
+ "model.layers.23.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00020-of-00024.bin",
555
+ "model.layers.23.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00020-of-00024.bin",
556
+ "model.layers.23.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00021-of-00024.bin",
557
+ "model.layers.23.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00021-of-00024.bin",
558
+ "model.layers.23.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00021-of-00024.bin",
559
+ "model.layers.23.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00021-of-00024.bin",
560
+ "model.layers.23.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00021-of-00024.bin",
561
+ "model.layers.23.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00021-of-00024.bin",
562
+ "model.layers.23.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00021-of-00024.bin",
563
+ "model.layers.23.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00021-of-00024.bin",
564
+ "model.layers.23.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00021-of-00024.bin",
565
+ "model.layers.23.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00021-of-00024.bin",
566
+ "model.layers.23.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00021-of-00024.bin",
567
+ "model.layers.23.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00021-of-00024.bin",
568
+ "model.layers.23.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00021-of-00024.bin",
569
+ "model.layers.23.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00021-of-00024.bin",
570
+ "model.layers.23.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00021-of-00024.bin",
571
+ "model.layers.23.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00021-of-00024.bin",
572
+ "model.layers.23.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00021-of-00024.bin",
573
+ "model.layers.23.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00021-of-00024.bin",
574
+ "model.layers.23.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00021-of-00024.bin",
575
+ "model.layers.23.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00021-of-00024.bin",
576
+ "model.layers.23.block_sparse_moe.gate.weight": "pytorch_model-00020-of-00024.bin",
577
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00021-of-00024.bin",
578
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00020-of-00024.bin",
579
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00020-of-00024.bin",
580
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00020-of-00024.bin",
581
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00021-of-00024.bin",
582
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00020-of-00024.bin",
583
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00020-of-00024.bin",
584
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00020-of-00024.bin",
585
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00020-of-00024.bin",
586
+ "model.layers.24.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00021-of-00024.bin",
587
+ "model.layers.24.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00021-of-00024.bin",
588
+ "model.layers.24.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00021-of-00024.bin",
589
+ "model.layers.24.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00021-of-00024.bin",
590
+ "model.layers.24.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00021-of-00024.bin",
591
+ "model.layers.24.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00021-of-00024.bin",
592
+ "model.layers.24.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00021-of-00024.bin",
593
+ "model.layers.24.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00021-of-00024.bin",
594
+ "model.layers.24.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00021-of-00024.bin",
595
+ "model.layers.24.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00022-of-00024.bin",
596
+ "model.layers.24.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00022-of-00024.bin",
597
+ "model.layers.24.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00022-of-00024.bin",
598
+ "model.layers.24.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00022-of-00024.bin",
599
+ "model.layers.24.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00022-of-00024.bin",
600
+ "model.layers.24.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00022-of-00024.bin",
601
+ "model.layers.24.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00022-of-00024.bin",
602
+ "model.layers.24.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00022-of-00024.bin",
603
+ "model.layers.24.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00022-of-00024.bin",
604
+ "model.layers.24.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00022-of-00024.bin",
605
+ "model.layers.24.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00022-of-00024.bin",
606
+ "model.layers.24.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00022-of-00024.bin",
607
+ "model.layers.24.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00022-of-00024.bin",
608
+ "model.layers.24.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00022-of-00024.bin",
609
+ "model.layers.24.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00022-of-00024.bin",
610
+ "model.layers.24.block_sparse_moe.gate.weight": "pytorch_model-00021-of-00024.bin",
611
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00022-of-00024.bin",
612
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00021-of-00024.bin",
613
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00021-of-00024.bin",
614
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00021-of-00024.bin",
615
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00022-of-00024.bin",
616
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00021-of-00024.bin",
617
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00021-of-00024.bin",
618
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00021-of-00024.bin",
619
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00021-of-00024.bin",
620
+ "model.layers.25.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00022-of-00024.bin",
621
+ "model.layers.25.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00022-of-00024.bin",
622
+ "model.layers.25.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00022-of-00024.bin",
623
+ "model.layers.25.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00022-of-00024.bin",
624
+ "model.layers.25.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00022-of-00024.bin",
625
+ "model.layers.25.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00022-of-00024.bin",
626
+ "model.layers.25.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00022-of-00024.bin",
627
+ "model.layers.25.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00022-of-00024.bin",
628
+ "model.layers.25.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00022-of-00024.bin",
629
+ "model.layers.25.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00022-of-00024.bin",
630
+ "model.layers.25.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00022-of-00024.bin",
631
+ "model.layers.25.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00022-of-00024.bin",
632
+ "model.layers.25.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00022-of-00024.bin",
633
+ "model.layers.25.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00022-of-00024.bin",
634
+ "model.layers.25.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00023-of-00024.bin",
635
+ "model.layers.25.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00023-of-00024.bin",
636
+ "model.layers.25.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00023-of-00024.bin",
637
+ "model.layers.25.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00023-of-00024.bin",
638
+ "model.layers.25.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00023-of-00024.bin",
639
+ "model.layers.25.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00023-of-00024.bin",
640
+ "model.layers.25.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00023-of-00024.bin",
641
+ "model.layers.25.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00023-of-00024.bin",
642
+ "model.layers.25.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00023-of-00024.bin",
643
+ "model.layers.25.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00023-of-00024.bin",
644
+ "model.layers.25.block_sparse_moe.gate.weight": "pytorch_model-00022-of-00024.bin",
645
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00023-of-00024.bin",
646
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00022-of-00024.bin",
647
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00022-of-00024.bin",
648
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00022-of-00024.bin",
649
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00023-of-00024.bin",
650
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00022-of-00024.bin",
651
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00022-of-00024.bin",
652
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00022-of-00024.bin",
653
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00022-of-00024.bin",
654
+ "model.layers.26.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00023-of-00024.bin",
655
+ "model.layers.26.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00023-of-00024.bin",
656
+ "model.layers.26.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00023-of-00024.bin",
657
+ "model.layers.26.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00023-of-00024.bin",
658
+ "model.layers.26.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00023-of-00024.bin",
659
+ "model.layers.26.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00023-of-00024.bin",
660
+ "model.layers.26.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00023-of-00024.bin",
661
+ "model.layers.26.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00023-of-00024.bin",
662
+ "model.layers.26.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00023-of-00024.bin",
663
+ "model.layers.26.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00023-of-00024.bin",
664
+ "model.layers.26.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00023-of-00024.bin",
665
+ "model.layers.26.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00023-of-00024.bin",
666
+ "model.layers.26.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00023-of-00024.bin",
667
+ "model.layers.26.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00023-of-00024.bin",
668
+ "model.layers.26.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00023-of-00024.bin",
669
+ "model.layers.26.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00023-of-00024.bin",
670
+ "model.layers.26.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00023-of-00024.bin",
671
+ "model.layers.26.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00023-of-00024.bin",
672
+ "model.layers.26.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00023-of-00024.bin",
673
+ "model.layers.26.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00024-of-00024.bin",
674
+ "model.layers.26.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00024-of-00024.bin",
675
+ "model.layers.26.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00024-of-00024.bin",
676
+ "model.layers.26.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00024-of-00024.bin",
677
+ "model.layers.26.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00024-of-00024.bin",
678
+ "model.layers.26.block_sparse_moe.gate.weight": "pytorch_model-00023-of-00024.bin",
679
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00024-of-00024.bin",
680
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00023-of-00024.bin",
681
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00023-of-00024.bin",
682
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00023-of-00024.bin",
683
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00024-of-00024.bin",
684
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00023-of-00024.bin",
685
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00023-of-00024.bin",
686
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00023-of-00024.bin",
687
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00023-of-00024.bin",
688
+ "model.layers.27.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00024-of-00024.bin",
689
+ "model.layers.27.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00024-of-00024.bin",
690
+ "model.layers.27.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00024-of-00024.bin",
691
+ "model.layers.27.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00024-of-00024.bin",
692
+ "model.layers.27.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00024-of-00024.bin",
693
+ "model.layers.27.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00024-of-00024.bin",
694
+ "model.layers.27.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00024-of-00024.bin",
695
+ "model.layers.27.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00024-of-00024.bin",
696
+ "model.layers.27.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00024-of-00024.bin",
697
+ "model.layers.27.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00024-of-00024.bin",
698
+ "model.layers.27.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00024-of-00024.bin",
699
+ "model.layers.27.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00024-of-00024.bin",
700
+ "model.layers.27.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00024-of-00024.bin",
701
+ "model.layers.27.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00024-of-00024.bin",
702
+ "model.layers.27.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00024-of-00024.bin",
703
+ "model.layers.27.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00024-of-00024.bin",
704
+ "model.layers.27.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00024-of-00024.bin",
705
+ "model.layers.27.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00024-of-00024.bin",
706
+ "model.layers.27.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00024-of-00024.bin",
707
+ "model.layers.27.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00024-of-00024.bin",
708
+ "model.layers.27.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00024-of-00024.bin",
709
+ "model.layers.27.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00024-of-00024.bin",
710
+ "model.layers.27.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00024-of-00024.bin",
711
+ "model.layers.27.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00024-of-00024.bin",
712
+ "model.layers.27.block_sparse_moe.gate.weight": "pytorch_model-00024-of-00024.bin",
713
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00024-of-00024.bin",
714
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00024-of-00024.bin",
715
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00024-of-00024.bin",
716
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00024-of-00024.bin",
717
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00024-of-00024.bin",
718
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00024-of-00024.bin",
719
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00024-of-00024.bin",
720
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00024-of-00024.bin",
721
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00024-of-00024.bin",
722
+ "model.layers.3.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00003-of-00024.bin",
723
+ "model.layers.3.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00003-of-00024.bin",
724
+ "model.layers.3.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00024.bin",
725
+ "model.layers.3.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00024.bin",
726
+ "model.layers.3.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00024.bin",
727
+ "model.layers.3.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00024.bin",
728
+ "model.layers.3.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00024.bin",
729
+ "model.layers.3.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00004-of-00024.bin",
730
+ "model.layers.3.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00004-of-00024.bin",
731
+ "model.layers.3.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00004-of-00024.bin",
732
+ "model.layers.3.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00004-of-00024.bin",
733
+ "model.layers.3.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00004-of-00024.bin",
734
+ "model.layers.3.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00004-of-00024.bin",
735
+ "model.layers.3.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00004-of-00024.bin",
736
+ "model.layers.3.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00004-of-00024.bin",
737
+ "model.layers.3.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00004-of-00024.bin",
738
+ "model.layers.3.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00004-of-00024.bin",
739
+ "model.layers.3.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00004-of-00024.bin",
740
+ "model.layers.3.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00004-of-00024.bin",
741
+ "model.layers.3.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00004-of-00024.bin",
742
+ "model.layers.3.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00004-of-00024.bin",
743
+ "model.layers.3.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00004-of-00024.bin",
744
+ "model.layers.3.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00004-of-00024.bin",
745
+ "model.layers.3.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00004-of-00024.bin",
746
+ "model.layers.3.block_sparse_moe.gate.weight": "pytorch_model-00003-of-00024.bin",
747
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00024.bin",
748
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00024.bin",
749
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00024.bin",
750
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00024.bin",
751
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00024.bin",
752
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00024.bin",
753
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00024.bin",
754
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00024.bin",
755
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00024.bin",
756
+ "model.layers.4.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00004-of-00024.bin",
757
+ "model.layers.4.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00004-of-00024.bin",
758
+ "model.layers.4.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00004-of-00024.bin",
759
+ "model.layers.4.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00004-of-00024.bin",
760
+ "model.layers.4.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00004-of-00024.bin",
761
+ "model.layers.4.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00004-of-00024.bin",
762
+ "model.layers.4.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00004-of-00024.bin",
763
+ "model.layers.4.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00024.bin",
764
+ "model.layers.4.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00024.bin",
765
+ "model.layers.4.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00024.bin",
766
+ "model.layers.4.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00024.bin",
767
+ "model.layers.4.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00024.bin",
768
+ "model.layers.4.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00005-of-00024.bin",
769
+ "model.layers.4.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00005-of-00024.bin",
770
+ "model.layers.4.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00005-of-00024.bin",
771
+ "model.layers.4.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00005-of-00024.bin",
772
+ "model.layers.4.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00005-of-00024.bin",
773
+ "model.layers.4.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00005-of-00024.bin",
774
+ "model.layers.4.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00005-of-00024.bin",
775
+ "model.layers.4.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00005-of-00024.bin",
776
+ "model.layers.4.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00005-of-00024.bin",
777
+ "model.layers.4.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00005-of-00024.bin",
778
+ "model.layers.4.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00005-of-00024.bin",
779
+ "model.layers.4.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00005-of-00024.bin",
780
+ "model.layers.4.block_sparse_moe.gate.weight": "pytorch_model-00004-of-00024.bin",
781
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00005-of-00024.bin",
782
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00024.bin",
783
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00024.bin",
784
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00024.bin",
785
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00005-of-00024.bin",
786
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00024.bin",
787
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00024.bin",
788
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00024.bin",
789
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00024.bin",
790
+ "model.layers.5.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00005-of-00024.bin",
791
+ "model.layers.5.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00005-of-00024.bin",
792
+ "model.layers.5.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00005-of-00024.bin",
793
+ "model.layers.5.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00005-of-00024.bin",
794
+ "model.layers.5.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00005-of-00024.bin",
795
+ "model.layers.5.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00005-of-00024.bin",
796
+ "model.layers.5.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00005-of-00024.bin",
797
+ "model.layers.5.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00005-of-00024.bin",
798
+ "model.layers.5.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00005-of-00024.bin",
799
+ "model.layers.5.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00005-of-00024.bin",
800
+ "model.layers.5.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00005-of-00024.bin",
801
+ "model.layers.5.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00005-of-00024.bin",
802
+ "model.layers.5.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00024.bin",
803
+ "model.layers.5.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00024.bin",
804
+ "model.layers.5.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00024.bin",
805
+ "model.layers.5.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00024.bin",
806
+ "model.layers.5.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00024.bin",
807
+ "model.layers.5.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00006-of-00024.bin",
808
+ "model.layers.5.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00006-of-00024.bin",
809
+ "model.layers.5.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00006-of-00024.bin",
810
+ "model.layers.5.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00006-of-00024.bin",
811
+ "model.layers.5.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00006-of-00024.bin",
812
+ "model.layers.5.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00006-of-00024.bin",
813
+ "model.layers.5.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00006-of-00024.bin",
814
+ "model.layers.5.block_sparse_moe.gate.weight": "pytorch_model-00005-of-00024.bin",
815
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00006-of-00024.bin",
816
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00024.bin",
817
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00024.bin",
818
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00024.bin",
819
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00006-of-00024.bin",
820
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00005-of-00024.bin",
821
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00024.bin",
822
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00005-of-00024.bin",
823
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00005-of-00024.bin",
824
+ "model.layers.6.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00006-of-00024.bin",
825
+ "model.layers.6.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00006-of-00024.bin",
826
+ "model.layers.6.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00006-of-00024.bin",
827
+ "model.layers.6.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00006-of-00024.bin",
828
+ "model.layers.6.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00006-of-00024.bin",
829
+ "model.layers.6.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00006-of-00024.bin",
830
+ "model.layers.6.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00006-of-00024.bin",
831
+ "model.layers.6.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00006-of-00024.bin",
832
+ "model.layers.6.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00006-of-00024.bin",
833
+ "model.layers.6.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00006-of-00024.bin",
834
+ "model.layers.6.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00006-of-00024.bin",
835
+ "model.layers.6.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00006-of-00024.bin",
836
+ "model.layers.6.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00006-of-00024.bin",
837
+ "model.layers.6.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00006-of-00024.bin",
838
+ "model.layers.6.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00006-of-00024.bin",
839
+ "model.layers.6.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00006-of-00024.bin",
840
+ "model.layers.6.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00006-of-00024.bin",
841
+ "model.layers.6.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00024.bin",
842
+ "model.layers.6.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00024.bin",
843
+ "model.layers.6.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00024.bin",
844
+ "model.layers.6.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00024.bin",
845
+ "model.layers.6.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00024.bin",
846
+ "model.layers.6.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00007-of-00024.bin",
847
+ "model.layers.6.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00007-of-00024.bin",
848
+ "model.layers.6.block_sparse_moe.gate.weight": "pytorch_model-00006-of-00024.bin",
849
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00024.bin",
850
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00024.bin",
851
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00006-of-00024.bin",
852
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00024.bin",
853
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00024.bin",
854
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00006-of-00024.bin",
855
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00006-of-00024.bin",
856
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00006-of-00024.bin",
857
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00006-of-00024.bin",
858
+ "model.layers.7.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00007-of-00024.bin",
859
+ "model.layers.7.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00007-of-00024.bin",
860
+ "model.layers.7.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00007-of-00024.bin",
861
+ "model.layers.7.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00007-of-00024.bin",
862
+ "model.layers.7.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00007-of-00024.bin",
863
+ "model.layers.7.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00007-of-00024.bin",
864
+ "model.layers.7.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00007-of-00024.bin",
865
+ "model.layers.7.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00007-of-00024.bin",
866
+ "model.layers.7.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00007-of-00024.bin",
867
+ "model.layers.7.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00007-of-00024.bin",
868
+ "model.layers.7.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00007-of-00024.bin",
869
+ "model.layers.7.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00007-of-00024.bin",
870
+ "model.layers.7.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00007-of-00024.bin",
871
+ "model.layers.7.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00007-of-00024.bin",
872
+ "model.layers.7.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00007-of-00024.bin",
873
+ "model.layers.7.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00007-of-00024.bin",
874
+ "model.layers.7.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00007-of-00024.bin",
875
+ "model.layers.7.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00007-of-00024.bin",
876
+ "model.layers.7.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00007-of-00024.bin",
877
+ "model.layers.7.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00007-of-00024.bin",
878
+ "model.layers.7.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00007-of-00024.bin",
879
+ "model.layers.7.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00007-of-00024.bin",
880
+ "model.layers.7.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00024.bin",
881
+ "model.layers.7.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00024.bin",
882
+ "model.layers.7.block_sparse_moe.gate.weight": "pytorch_model-00007-of-00024.bin",
883
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00008-of-00024.bin",
884
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00007-of-00024.bin",
885
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00007-of-00024.bin",
886
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00007-of-00024.bin",
887
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00008-of-00024.bin",
888
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00007-of-00024.bin",
889
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00007-of-00024.bin",
890
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00007-of-00024.bin",
891
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00007-of-00024.bin",
892
+ "model.layers.8.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00008-of-00024.bin",
893
+ "model.layers.8.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00008-of-00024.bin",
894
+ "model.layers.8.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00008-of-00024.bin",
895
+ "model.layers.8.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00008-of-00024.bin",
896
+ "model.layers.8.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00008-of-00024.bin",
897
+ "model.layers.8.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00008-of-00024.bin",
898
+ "model.layers.8.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00008-of-00024.bin",
899
+ "model.layers.8.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00008-of-00024.bin",
900
+ "model.layers.8.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00008-of-00024.bin",
901
+ "model.layers.8.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00008-of-00024.bin",
902
+ "model.layers.8.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00008-of-00024.bin",
903
+ "model.layers.8.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00008-of-00024.bin",
904
+ "model.layers.8.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00008-of-00024.bin",
905
+ "model.layers.8.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00008-of-00024.bin",
906
+ "model.layers.8.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00008-of-00024.bin",
907
+ "model.layers.8.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00008-of-00024.bin",
908
+ "model.layers.8.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00008-of-00024.bin",
909
+ "model.layers.8.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00008-of-00024.bin",
910
+ "model.layers.8.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00008-of-00024.bin",
911
+ "model.layers.8.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00008-of-00024.bin",
912
+ "model.layers.8.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00008-of-00024.bin",
913
+ "model.layers.8.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00008-of-00024.bin",
914
+ "model.layers.8.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00008-of-00024.bin",
915
+ "model.layers.8.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00008-of-00024.bin",
916
+ "model.layers.8.block_sparse_moe.gate.weight": "pytorch_model-00008-of-00024.bin",
917
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00008-of-00024.bin",
918
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00008-of-00024.bin",
919
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00008-of-00024.bin",
920
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00008-of-00024.bin",
921
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00008-of-00024.bin",
922
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00008-of-00024.bin",
923
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00008-of-00024.bin",
924
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00008-of-00024.bin",
925
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00008-of-00024.bin",
926
+ "model.layers.9.block_sparse_moe.experts.0.w1.weight": "pytorch_model-00009-of-00024.bin",
927
+ "model.layers.9.block_sparse_moe.experts.0.w2.weight": "pytorch_model-00009-of-00024.bin",
928
+ "model.layers.9.block_sparse_moe.experts.0.w3.weight": "pytorch_model-00009-of-00024.bin",
929
+ "model.layers.9.block_sparse_moe.experts.1.w1.weight": "pytorch_model-00009-of-00024.bin",
930
+ "model.layers.9.block_sparse_moe.experts.1.w2.weight": "pytorch_model-00009-of-00024.bin",
931
+ "model.layers.9.block_sparse_moe.experts.1.w3.weight": "pytorch_model-00009-of-00024.bin",
932
+ "model.layers.9.block_sparse_moe.experts.2.w1.weight": "pytorch_model-00009-of-00024.bin",
933
+ "model.layers.9.block_sparse_moe.experts.2.w2.weight": "pytorch_model-00009-of-00024.bin",
934
+ "model.layers.9.block_sparse_moe.experts.2.w3.weight": "pytorch_model-00009-of-00024.bin",
935
+ "model.layers.9.block_sparse_moe.experts.3.w1.weight": "pytorch_model-00009-of-00024.bin",
936
+ "model.layers.9.block_sparse_moe.experts.3.w2.weight": "pytorch_model-00009-of-00024.bin",
937
+ "model.layers.9.block_sparse_moe.experts.3.w3.weight": "pytorch_model-00009-of-00024.bin",
938
+ "model.layers.9.block_sparse_moe.experts.4.w1.weight": "pytorch_model-00009-of-00024.bin",
939
+ "model.layers.9.block_sparse_moe.experts.4.w2.weight": "pytorch_model-00009-of-00024.bin",
940
+ "model.layers.9.block_sparse_moe.experts.4.w3.weight": "pytorch_model-00009-of-00024.bin",
941
+ "model.layers.9.block_sparse_moe.experts.5.w1.weight": "pytorch_model-00009-of-00024.bin",
942
+ "model.layers.9.block_sparse_moe.experts.5.w2.weight": "pytorch_model-00009-of-00024.bin",
943
+ "model.layers.9.block_sparse_moe.experts.5.w3.weight": "pytorch_model-00009-of-00024.bin",
944
+ "model.layers.9.block_sparse_moe.experts.6.w1.weight": "pytorch_model-00009-of-00024.bin",
945
+ "model.layers.9.block_sparse_moe.experts.6.w2.weight": "pytorch_model-00009-of-00024.bin",
946
+ "model.layers.9.block_sparse_moe.experts.6.w3.weight": "pytorch_model-00009-of-00024.bin",
947
+ "model.layers.9.block_sparse_moe.experts.7.w1.weight": "pytorch_model-00009-of-00024.bin",
948
+ "model.layers.9.block_sparse_moe.experts.7.w2.weight": "pytorch_model-00009-of-00024.bin",
949
+ "model.layers.9.block_sparse_moe.experts.7.w3.weight": "pytorch_model-00009-of-00024.bin",
950
+ "model.layers.9.block_sparse_moe.gate.weight": "pytorch_model-00009-of-00024.bin",
951
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00009-of-00024.bin",
952
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00009-of-00024.bin",
953
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00008-of-00024.bin",
954
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00024.bin",
955
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00009-of-00024.bin",
956
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00008-of-00024.bin",
957
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00008-of-00024.bin",
958
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00008-of-00024.bin",
959
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00008-of-00024.bin",
960
+ "model.norm.weight": "pytorch_model-00024-of-00024.bin"
961
+ }
962
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<bos>",
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 sha256:16c7bb55a4086eff7c63d3a73bb0e92578ba318dee0a8b51f7fe128911268a7d
3
+ size 17477707
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<bos>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "<eos>",
41
+ "legacy": null,
42
+ "max_length": null,
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "pad_to_multiple_of": null,
45
+ "pad_token": "<bos>",
46
+ "pad_token_type_id": 0,
47
+ "padding_side": "left",
48
+ "sp_model_kwargs": {},
49
+ "spaces_between_special_tokens": false,
50
+ "tokenizer_class": "GemmaTokenizer",
51
+ "unk_token": "<unk>",
52
+ "use_default_system_prompt": false
53
+ }