Upload GPTNeoXForCausalLM

config.json

@@ -1,12 +1,14 @@
 {
-  "_name_or_path": "ko_en",
+  "_name_or_path": "train_v1.1b/ko_to_en",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classifier_dropout": 0.1,
   "eos_token_id": 2,
   "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 16384,
@@ -16,11 +18,12 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_steps": "global_step320000",
+  "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.32.0.dev0",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 30080

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "transformers_version": "4.29.2"
+  "transformers_version": "4.32.0.dev0"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30abd1ad02c53052487eb40af7bb2e811128b84c95235cba3870198a5147dac
-size 10017673915
+oid sha256:707f8f875916f70511650eadbf494d95dcc3f8d74f7aa465993c1b8e088f2528
+size 9912798457

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56484e0d9e5830ad8e3f14a669c67d173914ede517490e74301949dea94cab10
-size 1870040575
+oid sha256:5cbadbf224e3d37a5b655ee6160cf72c2837eecea34e9be37326cebb07fa1e4c
+size 1857455571

pytorch_model.bin.index.json

@@ -1,16 +1,14 @@
 {
   "metadata": {
-    "total_size": 11784801848.0
+    "total_size": 11770121728
   },
   "weight_map": {
     "embed_out.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -22,10 +20,8 @@
     "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -37,10 +33,8 @@
     "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -52,10 +46,8 @@
     "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -67,10 +59,8 @@
     "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -82,10 +72,8 @@
     "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -97,10 +85,8 @@
     "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -112,10 +98,8 @@
     "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -127,10 +111,8 @@
     "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.16.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -142,10 +124,8 @@
     "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.17.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -157,10 +137,8 @@
     "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.18.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -172,10 +150,8 @@
     "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.19.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -187,10 +163,8 @@
     "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -202,10 +176,8 @@
     "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.20.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -217,10 +189,8 @@
     "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.21.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -232,10 +202,8 @@
     "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.22.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -247,10 +215,8 @@
     "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.23.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -262,10 +228,8 @@
     "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.24.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -277,10 +241,8 @@
     "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
@@ -292,10 +254,8 @@
     "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
@@ -307,10 +267,8 @@
     "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
@@ -322,10 +280,8 @@
     "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
     "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
-    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -337,10 +293,8 @@
     "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -352,10 +306,8 @@
     "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -367,10 +319,8 @@
     "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -382,10 +332,8 @@
     "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -397,10 +345,8 @@
     "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
@@ -412,10 +358,8 @@
     "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
-    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
     "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",