beomi commited on
Commit
48a6670
1 Parent(s): d7bfe77

add safetensors sharded weights

Browse files
.gitattributes CHANGED
@@ -30,3 +30,31 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
33
+ model-00003-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
34
+ model-00022-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
35
+ model-00012-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
36
+ model-00021-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00005-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00028-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00025-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ model-00026-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
41
+ model-00027-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
42
+ model-00006-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
43
+ model-00008-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
44
+ model-00009-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
45
+ model-00015-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
46
+ model-00018-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
47
+ model-00020-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
48
+ model-00001-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
49
+ model-00007-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
50
+ model-00014-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
51
+ model-00013-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
52
+ model-00023-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
53
+ model-00024-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
54
+ model-00004-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
55
+ model-00010-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
56
+ model-00011-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
57
+ model-00019-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
58
+ model-00002-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
59
+ model-00016-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
60
+ model-00017-of-00028.safetensors filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1 +1,27 @@
1
- {"hidden_act": "gelu", "architectures": ["GPTNeoXForCausalLM"], "bos_token_id": 0, "eos_token_id": 0, "initializer_range": 0.02, "layer_norm_eps": 1e-05, "model_type": "gpt_neox", "hidden_size": 5120, "intermediate_size": 20480, "num_attention_heads": 40, "num_hidden_layers": 40, "max_position_embeddings": 2048, "rotary_pct": 0.5, "rotary_emb_base": 10000, "torch_dtype": "float16", "use_cache": true, "vocab_size": 30080, "num_steps": "global_step301000"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./polyglot-ko-12.8b/",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_steps": "global_step301000",
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.5,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.29.2",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 30080
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.29.2"
6
+ }
model-00001-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1077f2f2f2d1a4adda1ba69524723a3343e1c9af0c9d839e0818487700964a3
3
+ size 945730380
model-00002-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf66e85dfaa55d13d00c37bc84acde2290a387c1345290c18dbd2d34dd711d03
3
+ size 843231522
model-00003-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4725b4a4ca9469b1063fc393b0350ae368694a2c24a852a9b1ed44d98e2c72cf
3
+ size 843231290
model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b46da00378d9570cd8969063f680b6db2c2a045f778776652446c75258a6261
3
+ size 1004754108
model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947d464386804caf29f0b5e05cdc583eae20d44145ecd188405e0e0925d52291
3
+ size 895670546
model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11407a250b137bba535c36858f8a449532d364649bf526e8d5bbb312a1e3dac2
3
+ size 1004754108
model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c136a2a37e220233430fd98ef08f1a6b065c7de168be74a7cd33e5070276ce9
3
+ size 895670546
model-00008-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f134b18eaafcd76b161903985b5c0ab7ea1e9fd00fbbb5428a4c08975a8b5920
3
+ size 1004754132
model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62e7815e79e7408bb0a675690941e528498da56f044393100d44b1d361623bf
3
+ size 895670570
model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f151e74235be0f549323cba93a6003556b7e13d8480e27626d7db540b9db6bc6
3
+ size 1004754140
model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c3d6eec5f29e8e1939d4ab754341023d25692d816185be3fbac9b9901d97ae
3
+ size 895670570
model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfd157f5e29d53c0ed3ecad7ce30721b2dafde9c2092328facc5df5eff5fde3
3
+ size 1004754140
model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd724af69f86a500164cc1780478b7104afe3910ecc8c95cd516f550397f1c55
3
+ size 895670570
model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b110a8f23c20c659195f1b146c1b82e4717ea4955ea242a4318be3e7ae2025
3
+ size 1004754140
model-00015-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8323b729fb2df1177e357f7ecd96b25b142f0d024e920d21cf873fd6021326c1
3
+ size 895670570
model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ee1e2e803c1272e60f3eae7cccf9c68647608d52b79315ee52edf8a059b945
3
+ size 1004754140
model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb2de4ff8946b29a9776a2e0360f81d9cf02d6efbae6db26496d62cd01d87be
3
+ size 895670570
model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8337215210384ad9ac82b3efd260bc6c4c6a5fe1e51f4ba76f293e8844be1c
3
+ size 1004754140
model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027f7e1ced944fb2180a95cb42cbe5fc9ae98537c7d2500166688f15526307a7
3
+ size 895670570
model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac26f449546e6926433479c6acae25731adc9cb741f888050e5fc9562c28d1c
3
+ size 1004754140
model-00021-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bf23c027ad7d34408b03592bf1a6d4719b557ca7646096fe3e0523fda00e56
3
+ size 895670570
model-00022-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a5e1e407bf5a1c7dcfe71856b05a9eb7146a46012254c71a41c09de03d599c
3
+ size 1004754140
model-00023-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41993efaf3f39c8f244ce8fba2b199a9f3a46b524619dfe3c940a5211f4581ea
3
+ size 895670570
model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b41c91e41e3c4bee9d8a1474381e3e78c388fe889cfba2640f6f5265104164
3
+ size 1004754140
model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6074ebecce3abe57fa02f8f71c389945095831bc2795ce5e494f1be7a89fd35f
3
+ size 895670570
model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec350b1755ef7ac78bc353115e2eb15cb2e358a5505ccfedd9f2277cb4776548
3
+ size 1004754140
model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a9f7671a47acdfaa6a17f7492271a7b4339b7344aaed47429ade0bdf7f6e15
3
+ size 895670570
model-00028-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ea0188f126c4cd893bfdf40fbb5fb222da030f321ce595dfcf855887d72ead
3
+ size 517765688
model.safetensors.index.json ADDED
@@ -0,0 +1,611 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 25808184400.0
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00028-of-00028.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00028.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00028-of-00028.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00028-of-00028.safetensors",
10
+ "gpt_neox.layers.0.attention.bias": "model-00001-of-00028.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00028.safetensors",
12
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00028.safetensors",
13
+ "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00028.safetensors",
14
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00028.safetensors",
15
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00028.safetensors",
16
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00028.safetensors",
17
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00028.safetensors",
18
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00028.safetensors",
20
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00028.safetensors",
21
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00028.safetensors",
22
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00028.safetensors",
23
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00028.safetensors",
24
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
25
+ "gpt_neox.layers.1.attention.bias": "model-00001-of-00028.safetensors",
26
+ "gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00028.safetensors",
27
+ "gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00028.safetensors",
28
+ "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00028.safetensors",
29
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00028.safetensors",
30
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00028.safetensors",
31
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00028.safetensors",
32
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00028.safetensors",
33
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00028.safetensors",
34
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00028.safetensors",
35
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00028.safetensors",
36
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00028.safetensors",
37
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00028.safetensors",
38
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00028.safetensors",
39
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00028.safetensors",
40
+ "gpt_neox.layers.10.attention.bias": "model-00008-of-00028.safetensors",
41
+ "gpt_neox.layers.10.attention.dense.bias": "model-00008-of-00028.safetensors",
42
+ "gpt_neox.layers.10.attention.dense.weight": "model-00008-of-00028.safetensors",
43
+ "gpt_neox.layers.10.attention.masked_bias": "model-00008-of-00028.safetensors",
44
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00008-of-00028.safetensors",
45
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00008-of-00028.safetensors",
46
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00008-of-00028.safetensors",
47
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00008-of-00028.safetensors",
48
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00008-of-00028.safetensors",
49
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00008-of-00028.safetensors",
50
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00008-of-00028.safetensors",
51
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00008-of-00028.safetensors",
52
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00008-of-00028.safetensors",
53
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00008-of-00028.safetensors",
54
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
55
+ "gpt_neox.layers.11.attention.bias": "model-00008-of-00028.safetensors",
56
+ "gpt_neox.layers.11.attention.dense.bias": "model-00009-of-00028.safetensors",
57
+ "gpt_neox.layers.11.attention.dense.weight": "model-00009-of-00028.safetensors",
58
+ "gpt_neox.layers.11.attention.masked_bias": "model-00008-of-00028.safetensors",
59
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00008-of-00028.safetensors",
60
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00008-of-00028.safetensors",
61
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00008-of-00028.safetensors",
62
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00008-of-00028.safetensors",
63
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00008-of-00028.safetensors",
64
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00009-of-00028.safetensors",
65
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00009-of-00028.safetensors",
66
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00009-of-00028.safetensors",
67
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00009-of-00028.safetensors",
68
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00008-of-00028.safetensors",
69
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00008-of-00028.safetensors",
70
+ "gpt_neox.layers.12.attention.bias": "model-00009-of-00028.safetensors",
71
+ "gpt_neox.layers.12.attention.dense.bias": "model-00009-of-00028.safetensors",
72
+ "gpt_neox.layers.12.attention.dense.weight": "model-00009-of-00028.safetensors",
73
+ "gpt_neox.layers.12.attention.masked_bias": "model-00009-of-00028.safetensors",
74
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00009-of-00028.safetensors",
75
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00009-of-00028.safetensors",
76
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00009-of-00028.safetensors",
77
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00009-of-00028.safetensors",
78
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00009-of-00028.safetensors",
79
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00010-of-00028.safetensors",
80
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00010-of-00028.safetensors",
81
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00009-of-00028.safetensors",
82
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00009-of-00028.safetensors",
83
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00009-of-00028.safetensors",
84
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00009-of-00028.safetensors",
85
+ "gpt_neox.layers.13.attention.bias": "model-00010-of-00028.safetensors",
86
+ "gpt_neox.layers.13.attention.dense.bias": "model-00010-of-00028.safetensors",
87
+ "gpt_neox.layers.13.attention.dense.weight": "model-00010-of-00028.safetensors",
88
+ "gpt_neox.layers.13.attention.masked_bias": "model-00010-of-00028.safetensors",
89
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00010-of-00028.safetensors",
90
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00010-of-00028.safetensors",
91
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00010-of-00028.safetensors",
92
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00010-of-00028.safetensors",
93
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00010-of-00028.safetensors",
94
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00010-of-00028.safetensors",
95
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00010-of-00028.safetensors",
96
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00010-of-00028.safetensors",
97
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00010-of-00028.safetensors",
98
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00010-of-00028.safetensors",
99
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
100
+ "gpt_neox.layers.14.attention.bias": "model-00010-of-00028.safetensors",
101
+ "gpt_neox.layers.14.attention.dense.bias": "model-00011-of-00028.safetensors",
102
+ "gpt_neox.layers.14.attention.dense.weight": "model-00011-of-00028.safetensors",
103
+ "gpt_neox.layers.14.attention.masked_bias": "model-00010-of-00028.safetensors",
104
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00010-of-00028.safetensors",
105
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00010-of-00028.safetensors",
106
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00010-of-00028.safetensors",
107
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00010-of-00028.safetensors",
108
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00010-of-00028.safetensors",
109
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00011-of-00028.safetensors",
110
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00011-of-00028.safetensors",
111
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00011-of-00028.safetensors",
112
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00011-of-00028.safetensors",
113
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00010-of-00028.safetensors",
114
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00010-of-00028.safetensors",
115
+ "gpt_neox.layers.15.attention.bias": "model-00011-of-00028.safetensors",
116
+ "gpt_neox.layers.15.attention.dense.bias": "model-00011-of-00028.safetensors",
117
+ "gpt_neox.layers.15.attention.dense.weight": "model-00011-of-00028.safetensors",
118
+ "gpt_neox.layers.15.attention.masked_bias": "model-00011-of-00028.safetensors",
119
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00011-of-00028.safetensors",
120
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00011-of-00028.safetensors",
121
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00011-of-00028.safetensors",
122
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00011-of-00028.safetensors",
123
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00011-of-00028.safetensors",
124
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00012-of-00028.safetensors",
125
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00012-of-00028.safetensors",
126
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00011-of-00028.safetensors",
127
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00011-of-00028.safetensors",
128
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00011-of-00028.safetensors",
129
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00011-of-00028.safetensors",
130
+ "gpt_neox.layers.16.attention.bias": "model-00012-of-00028.safetensors",
131
+ "gpt_neox.layers.16.attention.dense.bias": "model-00012-of-00028.safetensors",
132
+ "gpt_neox.layers.16.attention.dense.weight": "model-00012-of-00028.safetensors",
133
+ "gpt_neox.layers.16.attention.masked_bias": "model-00012-of-00028.safetensors",
134
+ "gpt_neox.layers.16.attention.query_key_value.bias": "model-00012-of-00028.safetensors",
135
+ "gpt_neox.layers.16.attention.query_key_value.weight": "model-00012-of-00028.safetensors",
136
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00012-of-00028.safetensors",
137
+ "gpt_neox.layers.16.input_layernorm.bias": "model-00012-of-00028.safetensors",
138
+ "gpt_neox.layers.16.input_layernorm.weight": "model-00012-of-00028.safetensors",
139
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00012-of-00028.safetensors",
140
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00012-of-00028.safetensors",
141
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00012-of-00028.safetensors",
142
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00012-of-00028.safetensors",
143
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00012-of-00028.safetensors",
144
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
145
+ "gpt_neox.layers.17.attention.bias": "model-00012-of-00028.safetensors",
146
+ "gpt_neox.layers.17.attention.dense.bias": "model-00013-of-00028.safetensors",
147
+ "gpt_neox.layers.17.attention.dense.weight": "model-00013-of-00028.safetensors",
148
+ "gpt_neox.layers.17.attention.masked_bias": "model-00012-of-00028.safetensors",
149
+ "gpt_neox.layers.17.attention.query_key_value.bias": "model-00012-of-00028.safetensors",
150
+ "gpt_neox.layers.17.attention.query_key_value.weight": "model-00012-of-00028.safetensors",
151
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00012-of-00028.safetensors",
152
+ "gpt_neox.layers.17.input_layernorm.bias": "model-00012-of-00028.safetensors",
153
+ "gpt_neox.layers.17.input_layernorm.weight": "model-00012-of-00028.safetensors",
154
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00013-of-00028.safetensors",
155
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00013-of-00028.safetensors",
156
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00013-of-00028.safetensors",
157
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00013-of-00028.safetensors",
158
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00012-of-00028.safetensors",
159
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00012-of-00028.safetensors",
160
+ "gpt_neox.layers.18.attention.bias": "model-00013-of-00028.safetensors",
161
+ "gpt_neox.layers.18.attention.dense.bias": "model-00013-of-00028.safetensors",
162
+ "gpt_neox.layers.18.attention.dense.weight": "model-00013-of-00028.safetensors",
163
+ "gpt_neox.layers.18.attention.masked_bias": "model-00013-of-00028.safetensors",
164
+ "gpt_neox.layers.18.attention.query_key_value.bias": "model-00013-of-00028.safetensors",
165
+ "gpt_neox.layers.18.attention.query_key_value.weight": "model-00013-of-00028.safetensors",
166
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00013-of-00028.safetensors",
167
+ "gpt_neox.layers.18.input_layernorm.bias": "model-00013-of-00028.safetensors",
168
+ "gpt_neox.layers.18.input_layernorm.weight": "model-00013-of-00028.safetensors",
169
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00014-of-00028.safetensors",
170
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00014-of-00028.safetensors",
171
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00013-of-00028.safetensors",
172
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00013-of-00028.safetensors",
173
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00013-of-00028.safetensors",
174
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00013-of-00028.safetensors",
175
+ "gpt_neox.layers.19.attention.bias": "model-00014-of-00028.safetensors",
176
+ "gpt_neox.layers.19.attention.dense.bias": "model-00014-of-00028.safetensors",
177
+ "gpt_neox.layers.19.attention.dense.weight": "model-00014-of-00028.safetensors",
178
+ "gpt_neox.layers.19.attention.masked_bias": "model-00014-of-00028.safetensors",
179
+ "gpt_neox.layers.19.attention.query_key_value.bias": "model-00014-of-00028.safetensors",
180
+ "gpt_neox.layers.19.attention.query_key_value.weight": "model-00014-of-00028.safetensors",
181
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00014-of-00028.safetensors",
182
+ "gpt_neox.layers.19.input_layernorm.bias": "model-00014-of-00028.safetensors",
183
+ "gpt_neox.layers.19.input_layernorm.weight": "model-00014-of-00028.safetensors",
184
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00014-of-00028.safetensors",
185
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00014-of-00028.safetensors",
186
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00014-of-00028.safetensors",
187
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00014-of-00028.safetensors",
188
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00014-of-00028.safetensors",
189
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
190
+ "gpt_neox.layers.2.attention.bias": "model-00002-of-00028.safetensors",
191
+ "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00028.safetensors",
192
+ "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00028.safetensors",
193
+ "gpt_neox.layers.2.attention.masked_bias": "model-00002-of-00028.safetensors",
194
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00028.safetensors",
195
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00028.safetensors",
196
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00002-of-00028.safetensors",
197
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00028.safetensors",
198
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors",
199
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00003-of-00028.safetensors",
200
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00003-of-00028.safetensors",
201
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00003-of-00028.safetensors",
202
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00003-of-00028.safetensors",
203
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00028.safetensors",
204
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors",
205
+ "gpt_neox.layers.20.attention.bias": "model-00014-of-00028.safetensors",
206
+ "gpt_neox.layers.20.attention.dense.bias": "model-00015-of-00028.safetensors",
207
+ "gpt_neox.layers.20.attention.dense.weight": "model-00015-of-00028.safetensors",
208
+ "gpt_neox.layers.20.attention.masked_bias": "model-00014-of-00028.safetensors",
209
+ "gpt_neox.layers.20.attention.query_key_value.bias": "model-00014-of-00028.safetensors",
210
+ "gpt_neox.layers.20.attention.query_key_value.weight": "model-00014-of-00028.safetensors",
211
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00014-of-00028.safetensors",
212
+ "gpt_neox.layers.20.input_layernorm.bias": "model-00014-of-00028.safetensors",
213
+ "gpt_neox.layers.20.input_layernorm.weight": "model-00014-of-00028.safetensors",
214
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00015-of-00028.safetensors",
215
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00015-of-00028.safetensors",
216
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00015-of-00028.safetensors",
217
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00015-of-00028.safetensors",
218
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00014-of-00028.safetensors",
219
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00014-of-00028.safetensors",
220
+ "gpt_neox.layers.21.attention.bias": "model-00015-of-00028.safetensors",
221
+ "gpt_neox.layers.21.attention.dense.bias": "model-00015-of-00028.safetensors",
222
+ "gpt_neox.layers.21.attention.dense.weight": "model-00015-of-00028.safetensors",
223
+ "gpt_neox.layers.21.attention.masked_bias": "model-00015-of-00028.safetensors",
224
+ "gpt_neox.layers.21.attention.query_key_value.bias": "model-00015-of-00028.safetensors",
225
+ "gpt_neox.layers.21.attention.query_key_value.weight": "model-00015-of-00028.safetensors",
226
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00015-of-00028.safetensors",
227
+ "gpt_neox.layers.21.input_layernorm.bias": "model-00015-of-00028.safetensors",
228
+ "gpt_neox.layers.21.input_layernorm.weight": "model-00015-of-00028.safetensors",
229
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00016-of-00028.safetensors",
230
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00016-of-00028.safetensors",
231
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00015-of-00028.safetensors",
232
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00015-of-00028.safetensors",
233
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00015-of-00028.safetensors",
234
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00015-of-00028.safetensors",
235
+ "gpt_neox.layers.22.attention.bias": "model-00016-of-00028.safetensors",
236
+ "gpt_neox.layers.22.attention.dense.bias": "model-00016-of-00028.safetensors",
237
+ "gpt_neox.layers.22.attention.dense.weight": "model-00016-of-00028.safetensors",
238
+ "gpt_neox.layers.22.attention.masked_bias": "model-00016-of-00028.safetensors",
239
+ "gpt_neox.layers.22.attention.query_key_value.bias": "model-00016-of-00028.safetensors",
240
+ "gpt_neox.layers.22.attention.query_key_value.weight": "model-00016-of-00028.safetensors",
241
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00016-of-00028.safetensors",
242
+ "gpt_neox.layers.22.input_layernorm.bias": "model-00016-of-00028.safetensors",
243
+ "gpt_neox.layers.22.input_layernorm.weight": "model-00016-of-00028.safetensors",
244
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00016-of-00028.safetensors",
245
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00016-of-00028.safetensors",
246
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00016-of-00028.safetensors",
247
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00016-of-00028.safetensors",
248
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00016-of-00028.safetensors",
249
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
250
+ "gpt_neox.layers.23.attention.bias": "model-00016-of-00028.safetensors",
251
+ "gpt_neox.layers.23.attention.dense.bias": "model-00017-of-00028.safetensors",
252
+ "gpt_neox.layers.23.attention.dense.weight": "model-00017-of-00028.safetensors",
253
+ "gpt_neox.layers.23.attention.masked_bias": "model-00016-of-00028.safetensors",
254
+ "gpt_neox.layers.23.attention.query_key_value.bias": "model-00016-of-00028.safetensors",
255
+ "gpt_neox.layers.23.attention.query_key_value.weight": "model-00016-of-00028.safetensors",
256
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00016-of-00028.safetensors",
257
+ "gpt_neox.layers.23.input_layernorm.bias": "model-00016-of-00028.safetensors",
258
+ "gpt_neox.layers.23.input_layernorm.weight": "model-00016-of-00028.safetensors",
259
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00017-of-00028.safetensors",
260
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00017-of-00028.safetensors",
261
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00017-of-00028.safetensors",
262
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00017-of-00028.safetensors",
263
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00016-of-00028.safetensors",
264
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00016-of-00028.safetensors",
265
+ "gpt_neox.layers.24.attention.bias": "model-00017-of-00028.safetensors",
266
+ "gpt_neox.layers.24.attention.dense.bias": "model-00017-of-00028.safetensors",
267
+ "gpt_neox.layers.24.attention.dense.weight": "model-00017-of-00028.safetensors",
268
+ "gpt_neox.layers.24.attention.masked_bias": "model-00017-of-00028.safetensors",
269
+ "gpt_neox.layers.24.attention.query_key_value.bias": "model-00017-of-00028.safetensors",
270
+ "gpt_neox.layers.24.attention.query_key_value.weight": "model-00017-of-00028.safetensors",
271
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00017-of-00028.safetensors",
272
+ "gpt_neox.layers.24.input_layernorm.bias": "model-00017-of-00028.safetensors",
273
+ "gpt_neox.layers.24.input_layernorm.weight": "model-00017-of-00028.safetensors",
274
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00018-of-00028.safetensors",
275
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00018-of-00028.safetensors",
276
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00017-of-00028.safetensors",
277
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00017-of-00028.safetensors",
278
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00017-of-00028.safetensors",
279
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00017-of-00028.safetensors",
280
+ "gpt_neox.layers.25.attention.bias": "model-00018-of-00028.safetensors",
281
+ "gpt_neox.layers.25.attention.dense.bias": "model-00018-of-00028.safetensors",
282
+ "gpt_neox.layers.25.attention.dense.weight": "model-00018-of-00028.safetensors",
283
+ "gpt_neox.layers.25.attention.masked_bias": "model-00018-of-00028.safetensors",
284
+ "gpt_neox.layers.25.attention.query_key_value.bias": "model-00018-of-00028.safetensors",
285
+ "gpt_neox.layers.25.attention.query_key_value.weight": "model-00018-of-00028.safetensors",
286
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00018-of-00028.safetensors",
287
+ "gpt_neox.layers.25.input_layernorm.bias": "model-00018-of-00028.safetensors",
288
+ "gpt_neox.layers.25.input_layernorm.weight": "model-00018-of-00028.safetensors",
289
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00018-of-00028.safetensors",
290
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00018-of-00028.safetensors",
291
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00018-of-00028.safetensors",
292
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00018-of-00028.safetensors",
293
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00018-of-00028.safetensors",
294
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
295
+ "gpt_neox.layers.26.attention.bias": "model-00018-of-00028.safetensors",
296
+ "gpt_neox.layers.26.attention.dense.bias": "model-00019-of-00028.safetensors",
297
+ "gpt_neox.layers.26.attention.dense.weight": "model-00019-of-00028.safetensors",
298
+ "gpt_neox.layers.26.attention.masked_bias": "model-00018-of-00028.safetensors",
299
+ "gpt_neox.layers.26.attention.query_key_value.bias": "model-00018-of-00028.safetensors",
300
+ "gpt_neox.layers.26.attention.query_key_value.weight": "model-00018-of-00028.safetensors",
301
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00018-of-00028.safetensors",
302
+ "gpt_neox.layers.26.input_layernorm.bias": "model-00018-of-00028.safetensors",
303
+ "gpt_neox.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors",
304
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00019-of-00028.safetensors",
305
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00019-of-00028.safetensors",
306
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00019-of-00028.safetensors",
307
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00019-of-00028.safetensors",
308
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00018-of-00028.safetensors",
309
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors",
310
+ "gpt_neox.layers.27.attention.bias": "model-00019-of-00028.safetensors",
311
+ "gpt_neox.layers.27.attention.dense.bias": "model-00019-of-00028.safetensors",
312
+ "gpt_neox.layers.27.attention.dense.weight": "model-00019-of-00028.safetensors",
313
+ "gpt_neox.layers.27.attention.masked_bias": "model-00019-of-00028.safetensors",
314
+ "gpt_neox.layers.27.attention.query_key_value.bias": "model-00019-of-00028.safetensors",
315
+ "gpt_neox.layers.27.attention.query_key_value.weight": "model-00019-of-00028.safetensors",
316
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00019-of-00028.safetensors",
317
+ "gpt_neox.layers.27.input_layernorm.bias": "model-00019-of-00028.safetensors",
318
+ "gpt_neox.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors",
319
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00020-of-00028.safetensors",
320
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00020-of-00028.safetensors",
321
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00019-of-00028.safetensors",
322
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00019-of-00028.safetensors",
323
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00019-of-00028.safetensors",
324
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors",
325
+ "gpt_neox.layers.28.attention.bias": "model-00020-of-00028.safetensors",
326
+ "gpt_neox.layers.28.attention.dense.bias": "model-00020-of-00028.safetensors",
327
+ "gpt_neox.layers.28.attention.dense.weight": "model-00020-of-00028.safetensors",
328
+ "gpt_neox.layers.28.attention.masked_bias": "model-00020-of-00028.safetensors",
329
+ "gpt_neox.layers.28.attention.query_key_value.bias": "model-00020-of-00028.safetensors",
330
+ "gpt_neox.layers.28.attention.query_key_value.weight": "model-00020-of-00028.safetensors",
331
+ "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00020-of-00028.safetensors",
332
+ "gpt_neox.layers.28.input_layernorm.bias": "model-00020-of-00028.safetensors",
333
+ "gpt_neox.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors",
334
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00020-of-00028.safetensors",
335
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00020-of-00028.safetensors",
336
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00020-of-00028.safetensors",
337
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00020-of-00028.safetensors",
338
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00020-of-00028.safetensors",
339
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
340
+ "gpt_neox.layers.29.attention.bias": "model-00020-of-00028.safetensors",
341
+ "gpt_neox.layers.29.attention.dense.bias": "model-00021-of-00028.safetensors",
342
+ "gpt_neox.layers.29.attention.dense.weight": "model-00021-of-00028.safetensors",
343
+ "gpt_neox.layers.29.attention.masked_bias": "model-00020-of-00028.safetensors",
344
+ "gpt_neox.layers.29.attention.query_key_value.bias": "model-00020-of-00028.safetensors",
345
+ "gpt_neox.layers.29.attention.query_key_value.weight": "model-00020-of-00028.safetensors",
346
+ "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00020-of-00028.safetensors",
347
+ "gpt_neox.layers.29.input_layernorm.bias": "model-00020-of-00028.safetensors",
348
+ "gpt_neox.layers.29.input_layernorm.weight": "model-00020-of-00028.safetensors",
349
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00021-of-00028.safetensors",
350
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00021-of-00028.safetensors",
351
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00021-of-00028.safetensors",
352
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00021-of-00028.safetensors",
353
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00020-of-00028.safetensors",
354
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00020-of-00028.safetensors",
355
+ "gpt_neox.layers.3.attention.bias": "model-00003-of-00028.safetensors",
356
+ "gpt_neox.layers.3.attention.dense.bias": "model-00003-of-00028.safetensors",
357
+ "gpt_neox.layers.3.attention.dense.weight": "model-00003-of-00028.safetensors",
358
+ "gpt_neox.layers.3.attention.masked_bias": "model-00003-of-00028.safetensors",
359
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00003-of-00028.safetensors",
360
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00003-of-00028.safetensors",
361
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00003-of-00028.safetensors",
362
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00003-of-00028.safetensors",
363
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors",
364
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00004-of-00028.safetensors",
365
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00004-of-00028.safetensors",
366
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00003-of-00028.safetensors",
367
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00028.safetensors",
368
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00003-of-00028.safetensors",
369
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors",
370
+ "gpt_neox.layers.30.attention.bias": "model-00021-of-00028.safetensors",
371
+ "gpt_neox.layers.30.attention.dense.bias": "model-00021-of-00028.safetensors",
372
+ "gpt_neox.layers.30.attention.dense.weight": "model-00021-of-00028.safetensors",
373
+ "gpt_neox.layers.30.attention.masked_bias": "model-00021-of-00028.safetensors",
374
+ "gpt_neox.layers.30.attention.query_key_value.bias": "model-00021-of-00028.safetensors",
375
+ "gpt_neox.layers.30.attention.query_key_value.weight": "model-00021-of-00028.safetensors",
376
+ "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00021-of-00028.safetensors",
377
+ "gpt_neox.layers.30.input_layernorm.bias": "model-00021-of-00028.safetensors",
378
+ "gpt_neox.layers.30.input_layernorm.weight": "model-00021-of-00028.safetensors",
379
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00022-of-00028.safetensors",
380
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00022-of-00028.safetensors",
381
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00021-of-00028.safetensors",
382
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00021-of-00028.safetensors",
383
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00021-of-00028.safetensors",
384
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00021-of-00028.safetensors",
385
+ "gpt_neox.layers.31.attention.bias": "model-00022-of-00028.safetensors",
386
+ "gpt_neox.layers.31.attention.dense.bias": "model-00022-of-00028.safetensors",
387
+ "gpt_neox.layers.31.attention.dense.weight": "model-00022-of-00028.safetensors",
388
+ "gpt_neox.layers.31.attention.masked_bias": "model-00022-of-00028.safetensors",
389
+ "gpt_neox.layers.31.attention.query_key_value.bias": "model-00022-of-00028.safetensors",
390
+ "gpt_neox.layers.31.attention.query_key_value.weight": "model-00022-of-00028.safetensors",
391
+ "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00022-of-00028.safetensors",
392
+ "gpt_neox.layers.31.input_layernorm.bias": "model-00022-of-00028.safetensors",
393
+ "gpt_neox.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors",
394
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00022-of-00028.safetensors",
395
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00022-of-00028.safetensors",
396
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00022-of-00028.safetensors",
397
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00022-of-00028.safetensors",
398
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00022-of-00028.safetensors",
399
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
400
+ "gpt_neox.layers.32.attention.bias": "model-00022-of-00028.safetensors",
401
+ "gpt_neox.layers.32.attention.dense.bias": "model-00023-of-00028.safetensors",
402
+ "gpt_neox.layers.32.attention.dense.weight": "model-00023-of-00028.safetensors",
403
+ "gpt_neox.layers.32.attention.masked_bias": "model-00022-of-00028.safetensors",
404
+ "gpt_neox.layers.32.attention.query_key_value.bias": "model-00022-of-00028.safetensors",
405
+ "gpt_neox.layers.32.attention.query_key_value.weight": "model-00022-of-00028.safetensors",
406
+ "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00022-of-00028.safetensors",
407
+ "gpt_neox.layers.32.input_layernorm.bias": "model-00022-of-00028.safetensors",
408
+ "gpt_neox.layers.32.input_layernorm.weight": "model-00022-of-00028.safetensors",
409
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00023-of-00028.safetensors",
410
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00023-of-00028.safetensors",
411
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00023-of-00028.safetensors",
412
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00023-of-00028.safetensors",
413
+ "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00022-of-00028.safetensors",
414
+ "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00022-of-00028.safetensors",
415
+ "gpt_neox.layers.33.attention.bias": "model-00023-of-00028.safetensors",
416
+ "gpt_neox.layers.33.attention.dense.bias": "model-00023-of-00028.safetensors",
417
+ "gpt_neox.layers.33.attention.dense.weight": "model-00023-of-00028.safetensors",
418
+ "gpt_neox.layers.33.attention.masked_bias": "model-00023-of-00028.safetensors",
419
+ "gpt_neox.layers.33.attention.query_key_value.bias": "model-00023-of-00028.safetensors",
420
+ "gpt_neox.layers.33.attention.query_key_value.weight": "model-00023-of-00028.safetensors",
421
+ "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00023-of-00028.safetensors",
422
+ "gpt_neox.layers.33.input_layernorm.bias": "model-00023-of-00028.safetensors",
423
+ "gpt_neox.layers.33.input_layernorm.weight": "model-00023-of-00028.safetensors",
424
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00024-of-00028.safetensors",
425
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00024-of-00028.safetensors",
426
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00023-of-00028.safetensors",
427
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00023-of-00028.safetensors",
428
+ "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00023-of-00028.safetensors",
429
+ "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00023-of-00028.safetensors",
430
+ "gpt_neox.layers.34.attention.bias": "model-00024-of-00028.safetensors",
431
+ "gpt_neox.layers.34.attention.dense.bias": "model-00024-of-00028.safetensors",
432
+ "gpt_neox.layers.34.attention.dense.weight": "model-00024-of-00028.safetensors",
433
+ "gpt_neox.layers.34.attention.masked_bias": "model-00024-of-00028.safetensors",
434
+ "gpt_neox.layers.34.attention.query_key_value.bias": "model-00024-of-00028.safetensors",
435
+ "gpt_neox.layers.34.attention.query_key_value.weight": "model-00024-of-00028.safetensors",
436
+ "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00024-of-00028.safetensors",
437
+ "gpt_neox.layers.34.input_layernorm.bias": "model-00024-of-00028.safetensors",
438
+ "gpt_neox.layers.34.input_layernorm.weight": "model-00024-of-00028.safetensors",
439
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00024-of-00028.safetensors",
440
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00024-of-00028.safetensors",
441
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00024-of-00028.safetensors",
442
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00024-of-00028.safetensors",
443
+ "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00024-of-00028.safetensors",
444
+ "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
445
+ "gpt_neox.layers.35.attention.bias": "model-00024-of-00028.safetensors",
446
+ "gpt_neox.layers.35.attention.dense.bias": "model-00025-of-00028.safetensors",
447
+ "gpt_neox.layers.35.attention.dense.weight": "model-00025-of-00028.safetensors",
448
+ "gpt_neox.layers.35.attention.masked_bias": "model-00024-of-00028.safetensors",
449
+ "gpt_neox.layers.35.attention.query_key_value.bias": "model-00024-of-00028.safetensors",
450
+ "gpt_neox.layers.35.attention.query_key_value.weight": "model-00024-of-00028.safetensors",
451
+ "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00024-of-00028.safetensors",
452
+ "gpt_neox.layers.35.input_layernorm.bias": "model-00024-of-00028.safetensors",
453
+ "gpt_neox.layers.35.input_layernorm.weight": "model-00024-of-00028.safetensors",
454
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00025-of-00028.safetensors",
455
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00025-of-00028.safetensors",
456
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00025-of-00028.safetensors",
457
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00025-of-00028.safetensors",
458
+ "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00024-of-00028.safetensors",
459
+ "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00024-of-00028.safetensors",
460
+ "gpt_neox.layers.36.attention.bias": "model-00025-of-00028.safetensors",
461
+ "gpt_neox.layers.36.attention.dense.bias": "model-00025-of-00028.safetensors",
462
+ "gpt_neox.layers.36.attention.dense.weight": "model-00025-of-00028.safetensors",
463
+ "gpt_neox.layers.36.attention.masked_bias": "model-00025-of-00028.safetensors",
464
+ "gpt_neox.layers.36.attention.query_key_value.bias": "model-00025-of-00028.safetensors",
465
+ "gpt_neox.layers.36.attention.query_key_value.weight": "model-00025-of-00028.safetensors",
466
+ "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "model-00025-of-00028.safetensors",
467
+ "gpt_neox.layers.36.input_layernorm.bias": "model-00025-of-00028.safetensors",
468
+ "gpt_neox.layers.36.input_layernorm.weight": "model-00025-of-00028.safetensors",
469
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00026-of-00028.safetensors",
470
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00026-of-00028.safetensors",
471
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00025-of-00028.safetensors",
472
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00025-of-00028.safetensors",
473
+ "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00025-of-00028.safetensors",
474
+ "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00025-of-00028.safetensors",
475
+ "gpt_neox.layers.37.attention.bias": "model-00026-of-00028.safetensors",
476
+ "gpt_neox.layers.37.attention.dense.bias": "model-00026-of-00028.safetensors",
477
+ "gpt_neox.layers.37.attention.dense.weight": "model-00026-of-00028.safetensors",
478
+ "gpt_neox.layers.37.attention.masked_bias": "model-00026-of-00028.safetensors",
479
+ "gpt_neox.layers.37.attention.query_key_value.bias": "model-00026-of-00028.safetensors",
480
+ "gpt_neox.layers.37.attention.query_key_value.weight": "model-00026-of-00028.safetensors",
481
+ "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "model-00026-of-00028.safetensors",
482
+ "gpt_neox.layers.37.input_layernorm.bias": "model-00026-of-00028.safetensors",
483
+ "gpt_neox.layers.37.input_layernorm.weight": "model-00026-of-00028.safetensors",
484
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00026-of-00028.safetensors",
485
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00026-of-00028.safetensors",
486
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00026-of-00028.safetensors",
487
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00026-of-00028.safetensors",
488
+ "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00026-of-00028.safetensors",
489
+ "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
490
+ "gpt_neox.layers.38.attention.bias": "model-00026-of-00028.safetensors",
491
+ "gpt_neox.layers.38.attention.dense.bias": "model-00027-of-00028.safetensors",
492
+ "gpt_neox.layers.38.attention.dense.weight": "model-00027-of-00028.safetensors",
493
+ "gpt_neox.layers.38.attention.masked_bias": "model-00026-of-00028.safetensors",
494
+ "gpt_neox.layers.38.attention.query_key_value.bias": "model-00026-of-00028.safetensors",
495
+ "gpt_neox.layers.38.attention.query_key_value.weight": "model-00026-of-00028.safetensors",
496
+ "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "model-00026-of-00028.safetensors",
497
+ "gpt_neox.layers.38.input_layernorm.bias": "model-00026-of-00028.safetensors",
498
+ "gpt_neox.layers.38.input_layernorm.weight": "model-00026-of-00028.safetensors",
499
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00027-of-00028.safetensors",
500
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00027-of-00028.safetensors",
501
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00027-of-00028.safetensors",
502
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00027-of-00028.safetensors",
503
+ "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00026-of-00028.safetensors",
504
+ "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00026-of-00028.safetensors",
505
+ "gpt_neox.layers.39.attention.bias": "model-00027-of-00028.safetensors",
506
+ "gpt_neox.layers.39.attention.dense.bias": "model-00027-of-00028.safetensors",
507
+ "gpt_neox.layers.39.attention.dense.weight": "model-00027-of-00028.safetensors",
508
+ "gpt_neox.layers.39.attention.masked_bias": "model-00027-of-00028.safetensors",
509
+ "gpt_neox.layers.39.attention.query_key_value.bias": "model-00027-of-00028.safetensors",
510
+ "gpt_neox.layers.39.attention.query_key_value.weight": "model-00027-of-00028.safetensors",
511
+ "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "model-00027-of-00028.safetensors",
512
+ "gpt_neox.layers.39.input_layernorm.bias": "model-00027-of-00028.safetensors",
513
+ "gpt_neox.layers.39.input_layernorm.weight": "model-00027-of-00028.safetensors",
514
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00028-of-00028.safetensors",
515
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00028-of-00028.safetensors",
516
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00027-of-00028.safetensors",
517
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00027-of-00028.safetensors",
518
+ "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00027-of-00028.safetensors",
519
+ "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00027-of-00028.safetensors",
520
+ "gpt_neox.layers.4.attention.bias": "model-00004-of-00028.safetensors",
521
+ "gpt_neox.layers.4.attention.dense.bias": "model-00004-of-00028.safetensors",
522
+ "gpt_neox.layers.4.attention.dense.weight": "model-00004-of-00028.safetensors",
523
+ "gpt_neox.layers.4.attention.masked_bias": "model-00004-of-00028.safetensors",
524
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00004-of-00028.safetensors",
525
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00004-of-00028.safetensors",
526
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00004-of-00028.safetensors",
527
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00004-of-00028.safetensors",
528
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors",
529
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00004-of-00028.safetensors",
530
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00004-of-00028.safetensors",
531
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00004-of-00028.safetensors",
532
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00004-of-00028.safetensors",
533
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00004-of-00028.safetensors",
534
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
535
+ "gpt_neox.layers.5.attention.bias": "model-00004-of-00028.safetensors",
536
+ "gpt_neox.layers.5.attention.dense.bias": "model-00005-of-00028.safetensors",
537
+ "gpt_neox.layers.5.attention.dense.weight": "model-00005-of-00028.safetensors",
538
+ "gpt_neox.layers.5.attention.masked_bias": "model-00004-of-00028.safetensors",
539
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00004-of-00028.safetensors",
540
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00004-of-00028.safetensors",
541
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00004-of-00028.safetensors",
542
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00004-of-00028.safetensors",
543
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00004-of-00028.safetensors",
544
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00005-of-00028.safetensors",
545
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00005-of-00028.safetensors",
546
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00005-of-00028.safetensors",
547
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00005-of-00028.safetensors",
548
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00004-of-00028.safetensors",
549
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00004-of-00028.safetensors",
550
+ "gpt_neox.layers.6.attention.bias": "model-00005-of-00028.safetensors",
551
+ "gpt_neox.layers.6.attention.dense.bias": "model-00005-of-00028.safetensors",
552
+ "gpt_neox.layers.6.attention.dense.weight": "model-00005-of-00028.safetensors",
553
+ "gpt_neox.layers.6.attention.masked_bias": "model-00005-of-00028.safetensors",
554
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00005-of-00028.safetensors",
555
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00005-of-00028.safetensors",
556
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00005-of-00028.safetensors",
557
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00005-of-00028.safetensors",
558
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00005-of-00028.safetensors",
559
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00006-of-00028.safetensors",
560
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00006-of-00028.safetensors",
561
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00005-of-00028.safetensors",
562
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00005-of-00028.safetensors",
563
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00005-of-00028.safetensors",
564
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00005-of-00028.safetensors",
565
+ "gpt_neox.layers.7.attention.bias": "model-00006-of-00028.safetensors",
566
+ "gpt_neox.layers.7.attention.dense.bias": "model-00006-of-00028.safetensors",
567
+ "gpt_neox.layers.7.attention.dense.weight": "model-00006-of-00028.safetensors",
568
+ "gpt_neox.layers.7.attention.masked_bias": "model-00006-of-00028.safetensors",
569
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00006-of-00028.safetensors",
570
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00006-of-00028.safetensors",
571
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00006-of-00028.safetensors",
572
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00006-of-00028.safetensors",
573
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00006-of-00028.safetensors",
574
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00006-of-00028.safetensors",
575
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00006-of-00028.safetensors",
576
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00006-of-00028.safetensors",
577
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00006-of-00028.safetensors",
578
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00006-of-00028.safetensors",
579
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
580
+ "gpt_neox.layers.8.attention.bias": "model-00006-of-00028.safetensors",
581
+ "gpt_neox.layers.8.attention.dense.bias": "model-00007-of-00028.safetensors",
582
+ "gpt_neox.layers.8.attention.dense.weight": "model-00007-of-00028.safetensors",
583
+ "gpt_neox.layers.8.attention.masked_bias": "model-00006-of-00028.safetensors",
584
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00006-of-00028.safetensors",
585
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00006-of-00028.safetensors",
586
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00006-of-00028.safetensors",
587
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00006-of-00028.safetensors",
588
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00006-of-00028.safetensors",
589
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00007-of-00028.safetensors",
590
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00007-of-00028.safetensors",
591
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00007-of-00028.safetensors",
592
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00007-of-00028.safetensors",
593
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00006-of-00028.safetensors",
594
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00006-of-00028.safetensors",
595
+ "gpt_neox.layers.9.attention.bias": "model-00007-of-00028.safetensors",
596
+ "gpt_neox.layers.9.attention.dense.bias": "model-00007-of-00028.safetensors",
597
+ "gpt_neox.layers.9.attention.dense.weight": "model-00007-of-00028.safetensors",
598
+ "gpt_neox.layers.9.attention.masked_bias": "model-00007-of-00028.safetensors",
599
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00007-of-00028.safetensors",
600
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00007-of-00028.safetensors",
601
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00007-of-00028.safetensors",
602
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00007-of-00028.safetensors",
603
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00007-of-00028.safetensors",
604
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00008-of-00028.safetensors",
605
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00008-of-00028.safetensors",
606
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00007-of-00028.safetensors",
607
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00007-of-00028.safetensors",
608
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00007-of-00028.safetensors",
609
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00007-of-00028.safetensors"
610
+ }
611
+ }