Upload 59 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "apply_residual_connection_post_layernorm": false,
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "unk_token_id": 0,
+  "hidden_dropout": 0.0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_embed": 1536,
+  "n_inner": null,
+  "n_layer": 24,
+  "num_attention_heads": 16,
+  "offset_alibi": 100,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "transformers_version": "4.20.0",
+  "use_cache": true,
+  "vocab_size": 250880
+}

model_00001-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc0ab1034e852fcc45a4507f8b219b801d1dc9b673ee6b165c6a3dd9a64bfd7
+size 770709840

model_00002-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323f2f8d69c5b580b86af15b7ed9573b52e09dfd2ab16847a038d4707ce5f432
+size 56664264

model_00003-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcfcaff173b21b8b952647082bca4396e7903591e0b618b07a17158898dba9c
+size 56664264

model_00004-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06bf96319c892e9a565d4cb5b57236417ce8739afd77ccd5cf3563e331f5285d
+size 56664264

model_00005-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20af575bec75b179d21eb0a21d8425875c686ade46b9569c5a933ab423d26a24
+size 56664264

model_00006-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057c0bb0623aad3012507f115e2886f94045f9fb623f4fc48404214fe0cb869d
+size 56664264

model_00007-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b526681aaeb83424ef29e6259f5b4c0480cd49ea5c62d53354de10ce6e5cc8
+size 56664264

model_00008-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16eee89753711e948077e1a0c9454083443eb92f33dc4509df43fde784c02bba
+size 56664264

model_00009-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bbc62f7508a071bcf43e66570cc19de077c37775b28daadf9599ebcb47cc8b
+size 56664264

model_00010-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f45d23326732b551e311f6687310d424ff42b5ad4dcd0298a29985fe744f44c
+size 56664264

model_00011-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8977110f765ca7f04682c83ac89dea59392f5e91f24f86cda62ba2e1bb82a5
+size 56664264

model_00012-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b73577163af281f8857a86918def71a003b5dd179ff7e0be3d299c84a087482
+size 56664280

model_00013-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5580cb5bcf3c53e349ae21931dc592201c6b0051f4b6cc1eb96c300fa1a51bce
+size 56664280

model_00014-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d01c363c580e39bbf4cbde676428f70871baf28ca7f22acf25293c8778c7b55
+size 56664280

model_00015-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d6d2970207027d526b5d317a42ea77ff48079a74fdce27c754cbd158ef7150
+size 56664280

model_00016-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c7c19e9065815f94616cdc0889eba750245b6173771c46e1295ba73b45438e
+size 56664280

model_00017-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3693be88cfec1478e8c5d88400c1f0df91a42515c59ace2be81028c3240b2c0
+size 56664280

model_00018-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccc3537231c1ceb6e2e972a4c750e641470d5864d2e3e17b5fd6de669e8082c
+size 56664280

model_00019-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5063ad85e42b1973c2349505990ec8e411f940b4390ca6fa5a50a95e2c908473
+size 56664280

model_00020-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b04c8c1ab5dbdd649a2759d0b105cf10647a5d29b5cdd0bd2c9291cb742c41
+size 56664280

model_00021-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db4720514c79736b008f9bc2ad0d23f9c6667bc624d0b117c55d5dad0de1adf
+size 56664280

model_00022-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b509449d355075e9097d8afef0ace85a7ae315ecb7a4427ba71aaf66e3d3dc9
+size 56664280

model_00023-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82181963de98b7a255336ae3019fb75b3792fe2dd2f19ec86af820e712b383b5
+size 56664280

model_00024-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c26b0717933b68dd40086ccd9ce5cef930599d60ba81747cfc022ebc6a15db
+size 56664280

model_00025-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970b69147eeeee56235695ba605d7718fc31c68ae8a32e57fcd16ef4e0081f75
+size 56664280

model_00026-of-00026.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c20964ae9e1b0c34f466a74252e18910d23413e9da69232f77139d98928ca1
+size 6328

pytorch_model.bin.index.json

@@ -0,0 +1,300 @@
+{
+  "metadata": {
+    "total_size": 2130628608
+  },
+  "weight_map": {
+    "h.0.input_layernorm.bias": "pytorch_model_00002-of-00026.bin",
+    "h.0.input_layernorm.weight": "pytorch_model_00002-of-00026.bin",
+    "h.0.mlp.dense_4h_to_h.bias": "pytorch_model_00002-of-00026.bin",
+    "h.0.mlp.dense_4h_to_h.weight": "pytorch_model_00002-of-00026.bin",
+    "h.0.mlp.dense_h_to_4h.bias": "pytorch_model_00002-of-00026.bin",
+    "h.0.mlp.dense_h_to_4h.weight": "pytorch_model_00002-of-00026.bin",
+    "h.0.post_attention_layernorm.bias": "pytorch_model_00002-of-00026.bin",
+    "h.0.post_attention_layernorm.weight": "pytorch_model_00002-of-00026.bin",
+    "h.0.self_attention.dense.bias": "pytorch_model_00002-of-00026.bin",
+    "h.0.self_attention.dense.weight": "pytorch_model_00002-of-00026.bin",
+    "h.0.self_attention.query_key_value.bias": "pytorch_model_00002-of-00026.bin",
+    "h.0.self_attention.query_key_value.weight": "pytorch_model_00002-of-00026.bin",
+    "h.1.input_layernorm.bias": "pytorch_model_00003-of-00026.bin",
+    "h.1.input_layernorm.weight": "pytorch_model_00003-of-00026.bin",
+    "h.1.mlp.dense_4h_to_h.bias": "pytorch_model_00003-of-00026.bin",
+    "h.1.mlp.dense_4h_to_h.weight": "pytorch_model_00003-of-00026.bin",
+    "h.1.mlp.dense_h_to_4h.bias": "pytorch_model_00003-of-00026.bin",
+    "h.1.mlp.dense_h_to_4h.weight": "pytorch_model_00003-of-00026.bin",
+    "h.1.post_attention_layernorm.bias": "pytorch_model_00003-of-00026.bin",
+    "h.1.post_attention_layernorm.weight": "pytorch_model_00003-of-00026.bin",
+    "h.1.self_attention.dense.bias": "pytorch_model_00003-of-00026.bin",
+    "h.1.self_attention.dense.weight": "pytorch_model_00003-of-00026.bin",
+    "h.1.self_attention.query_key_value.bias": "pytorch_model_00003-of-00026.bin",
+    "h.1.self_attention.query_key_value.weight": "pytorch_model_00003-of-00026.bin",
+    "h.10.input_layernorm.bias": "pytorch_model_00012-of-00026.bin",
+    "h.10.input_layernorm.weight": "pytorch_model_00012-of-00026.bin",
+    "h.10.mlp.dense_4h_to_h.bias": "pytorch_model_00012-of-00026.bin",
+    "h.10.mlp.dense_4h_to_h.weight": "pytorch_model_00012-of-00026.bin",
+    "h.10.mlp.dense_h_to_4h.bias": "pytorch_model_00012-of-00026.bin",
+    "h.10.mlp.dense_h_to_4h.weight": "pytorch_model_00012-of-00026.bin",
+    "h.10.post_attention_layernorm.bias": "pytorch_model_00012-of-00026.bin",
+    "h.10.post_attention_layernorm.weight": "pytorch_model_00012-of-00026.bin",
+    "h.10.self_attention.dense.bias": "pytorch_model_00012-of-00026.bin",
+    "h.10.self_attention.dense.weight": "pytorch_model_00012-of-00026.bin",
+    "h.10.self_attention.query_key_value.bias": "pytorch_model_00012-of-00026.bin",
+    "h.10.self_attention.query_key_value.weight": "pytorch_model_00012-of-00026.bin",
+    "h.11.input_layernorm.bias": "pytorch_model_00013-of-00026.bin",
+    "h.11.input_layernorm.weight": "pytorch_model_00013-of-00026.bin",
+    "h.11.mlp.dense_4h_to_h.bias": "pytorch_model_00013-of-00026.bin",
+    "h.11.mlp.dense_4h_to_h.weight": "pytorch_model_00013-of-00026.bin",
+    "h.11.mlp.dense_h_to_4h.bias": "pytorch_model_00013-of-00026.bin",
+    "h.11.mlp.dense_h_to_4h.weight": "pytorch_model_00013-of-00026.bin",
+    "h.11.post_attention_layernorm.bias": "pytorch_model_00013-of-00026.bin",
+    "h.11.post_attention_layernorm.weight": "pytorch_model_00013-of-00026.bin",
+    "h.11.self_attention.dense.bias": "pytorch_model_00013-of-00026.bin",
+    "h.11.self_attention.dense.weight": "pytorch_model_00013-of-00026.bin",
+    "h.11.self_attention.query_key_value.bias": "pytorch_model_00013-of-00026.bin",
+    "h.11.self_attention.query_key_value.weight": "pytorch_model_00013-of-00026.bin",
+    "h.12.input_layernorm.bias": "pytorch_model_00014-of-00026.bin",
+    "h.12.input_layernorm.weight": "pytorch_model_00014-of-00026.bin",
+    "h.12.mlp.dense_4h_to_h.bias": "pytorch_model_00014-of-00026.bin",
+    "h.12.mlp.dense_4h_to_h.weight": "pytorch_model_00014-of-00026.bin",
+    "h.12.mlp.dense_h_to_4h.bias": "pytorch_model_00014-of-00026.bin",
+    "h.12.mlp.dense_h_to_4h.weight": "pytorch_model_00014-of-00026.bin",
+    "h.12.post_attention_layernorm.bias": "pytorch_model_00014-of-00026.bin",
+    "h.12.post_attention_layernorm.weight": "pytorch_model_00014-of-00026.bin",
+    "h.12.self_attention.dense.bias": "pytorch_model_00014-of-00026.bin",
+    "h.12.self_attention.dense.weight": "pytorch_model_00014-of-00026.bin",
+    "h.12.self_attention.query_key_value.bias": "pytorch_model_00014-of-00026.bin",
+    "h.12.self_attention.query_key_value.weight": "pytorch_model_00014-of-00026.bin",
+    "h.13.input_layernorm.bias": "pytorch_model_00015-of-00026.bin",
+    "h.13.input_layernorm.weight": "pytorch_model_00015-of-00026.bin",
+    "h.13.mlp.dense_4h_to_h.bias": "pytorch_model_00015-of-00026.bin",
+    "h.13.mlp.dense_4h_to_h.weight": "pytorch_model_00015-of-00026.bin",
+    "h.13.mlp.dense_h_to_4h.bias": "pytorch_model_00015-of-00026.bin",
+    "h.13.mlp.dense_h_to_4h.weight": "pytorch_model_00015-of-00026.bin",
+    "h.13.post_attention_layernorm.bias": "pytorch_model_00015-of-00026.bin",
+    "h.13.post_attention_layernorm.weight": "pytorch_model_00015-of-00026.bin",
+    "h.13.self_attention.dense.bias": "pytorch_model_00015-of-00026.bin",
+    "h.13.self_attention.dense.weight": "pytorch_model_00015-of-00026.bin",
+    "h.13.self_attention.query_key_value.bias": "pytorch_model_00015-of-00026.bin",
+    "h.13.self_attention.query_key_value.weight": "pytorch_model_00015-of-00026.bin",
+    "h.14.input_layernorm.bias": "pytorch_model_00016-of-00026.bin",
+    "h.14.input_layernorm.weight": "pytorch_model_00016-of-00026.bin",
+    "h.14.mlp.dense_4h_to_h.bias": "pytorch_model_00016-of-00026.bin",
+    "h.14.mlp.dense_4h_to_h.weight": "pytorch_model_00016-of-00026.bin",
+    "h.14.mlp.dense_h_to_4h.bias": "pytorch_model_00016-of-00026.bin",
+    "h.14.mlp.dense_h_to_4h.weight": "pytorch_model_00016-of-00026.bin",
+    "h.14.post_attention_layernorm.bias": "pytorch_model_00016-of-00026.bin",
+    "h.14.post_attention_layernorm.weight": "pytorch_model_00016-of-00026.bin",
+    "h.14.self_attention.dense.bias": "pytorch_model_00016-of-00026.bin",
+    "h.14.self_attention.dense.weight": "pytorch_model_00016-of-00026.bin",
+    "h.14.self_attention.query_key_value.bias": "pytorch_model_00016-of-00026.bin",
+    "h.14.self_attention.query_key_value.weight": "pytorch_model_00016-of-00026.bin",
+    "h.15.input_layernorm.bias": "pytorch_model_00017-of-00026.bin",
+    "h.15.input_layernorm.weight": "pytorch_model_00017-of-00026.bin",
+    "h.15.mlp.dense_4h_to_h.bias": "pytorch_model_00017-of-00026.bin",
+    "h.15.mlp.dense_4h_to_h.weight": "pytorch_model_00017-of-00026.bin",
+    "h.15.mlp.dense_h_to_4h.bias": "pytorch_model_00017-of-00026.bin",
+    "h.15.mlp.dense_h_to_4h.weight": "pytorch_model_00017-of-00026.bin",
+    "h.15.post_attention_layernorm.bias": "pytorch_model_00017-of-00026.bin",
+    "h.15.post_attention_layernorm.weight": "pytorch_model_00017-of-00026.bin",
+    "h.15.self_attention.dense.bias": "pytorch_model_00017-of-00026.bin",
+    "h.15.self_attention.dense.weight": "pytorch_model_00017-of-00026.bin",
+    "h.15.self_attention.query_key_value.bias": "pytorch_model_00017-of-00026.bin",
+    "h.15.self_attention.query_key_value.weight": "pytorch_model_00017-of-00026.bin",
+    "h.16.input_layernorm.bias": "pytorch_model_00018-of-00026.bin",
+    "h.16.input_layernorm.weight": "pytorch_model_00018-of-00026.bin",
+    "h.16.mlp.dense_4h_to_h.bias": "pytorch_model_00018-of-00026.bin",
+    "h.16.mlp.dense_4h_to_h.weight": "pytorch_model_00018-of-00026.bin",
+    "h.16.mlp.dense_h_to_4h.bias": "pytorch_model_00018-of-00026.bin",
+    "h.16.mlp.dense_h_to_4h.weight": "pytorch_model_00018-of-00026.bin",
+    "h.16.post_attention_layernorm.bias": "pytorch_model_00018-of-00026.bin",
+    "h.16.post_attention_layernorm.weight": "pytorch_model_00018-of-00026.bin",
+    "h.16.self_attention.dense.bias": "pytorch_model_00018-of-00026.bin",
+    "h.16.self_attention.dense.weight": "pytorch_model_00018-of-00026.bin",
+    "h.16.self_attention.query_key_value.bias": "pytorch_model_00018-of-00026.bin",
+    "h.16.self_attention.query_key_value.weight": "pytorch_model_00018-of-00026.bin",
+    "h.17.input_layernorm.bias": "pytorch_model_00019-of-00026.bin",
+    "h.17.input_layernorm.weight": "pytorch_model_00019-of-00026.bin",
+    "h.17.mlp.dense_4h_to_h.bias": "pytorch_model_00019-of-00026.bin",
+    "h.17.mlp.dense_4h_to_h.weight": "pytorch_model_00019-of-00026.bin",
+    "h.17.mlp.dense_h_to_4h.bias": "pytorch_model_00019-of-00026.bin",
+    "h.17.mlp.dense_h_to_4h.weight": "pytorch_model_00019-of-00026.bin",
+    "h.17.post_attention_layernorm.bias": "pytorch_model_00019-of-00026.bin",
+    "h.17.post_attention_layernorm.weight": "pytorch_model_00019-of-00026.bin",
+    "h.17.self_attention.dense.bias": "pytorch_model_00019-of-00026.bin",
+    "h.17.self_attention.dense.weight": "pytorch_model_00019-of-00026.bin",
+    "h.17.self_attention.query_key_value.bias": "pytorch_model_00019-of-00026.bin",
+    "h.17.self_attention.query_key_value.weight": "pytorch_model_00019-of-00026.bin",
+    "h.18.input_layernorm.bias": "pytorch_model_00020-of-00026.bin",
+    "h.18.input_layernorm.weight": "pytorch_model_00020-of-00026.bin",
+    "h.18.mlp.dense_4h_to_h.bias": "pytorch_model_00020-of-00026.bin",
+    "h.18.mlp.dense_4h_to_h.weight": "pytorch_model_00020-of-00026.bin",
+    "h.18.mlp.dense_h_to_4h.bias": "pytorch_model_00020-of-00026.bin",
+    "h.18.mlp.dense_h_to_4h.weight": "pytorch_model_00020-of-00026.bin",
+    "h.18.post_attention_layernorm.bias": "pytorch_model_00020-of-00026.bin",
+    "h.18.post_attention_layernorm.weight": "pytorch_model_00020-of-00026.bin",
+    "h.18.self_attention.dense.bias": "pytorch_model_00020-of-00026.bin",
+    "h.18.self_attention.dense.weight": "pytorch_model_00020-of-00026.bin",
+    "h.18.self_attention.query_key_value.bias": "pytorch_model_00020-of-00026.bin",
+    "h.18.self_attention.query_key_value.weight": "pytorch_model_00020-of-00026.bin",
+    "h.19.input_layernorm.bias": "pytorch_model_00021-of-00026.bin",
+    "h.19.input_layernorm.weight": "pytorch_model_00021-of-00026.bin",
+    "h.19.mlp.dense_4h_to_h.bias": "pytorch_model_00021-of-00026.bin",
+    "h.19.mlp.dense_4h_to_h.weight": "pytorch_model_00021-of-00026.bin",
+    "h.19.mlp.dense_h_to_4h.bias": "pytorch_model_00021-of-00026.bin",
+    "h.19.mlp.dense_h_to_4h.weight": "pytorch_model_00021-of-00026.bin",
+    "h.19.post_attention_layernorm.bias": "pytorch_model_00021-of-00026.bin",
+    "h.19.post_attention_layernorm.weight": "pytorch_model_00021-of-00026.bin",
+    "h.19.self_attention.dense.bias": "pytorch_model_00021-of-00026.bin",
+    "h.19.self_attention.dense.weight": "pytorch_model_00021-of-00026.bin",
+    "h.19.self_attention.query_key_value.bias": "pytorch_model_00021-of-00026.bin",
+    "h.19.self_attention.query_key_value.weight": "pytorch_model_00021-of-00026.bin",
+    "h.2.input_layernorm.bias": "pytorch_model_00004-of-00026.bin",
+    "h.2.input_layernorm.weight": "pytorch_model_00004-of-00026.bin",
+    "h.2.mlp.dense_4h_to_h.bias": "pytorch_model_00004-of-00026.bin",
+    "h.2.mlp.dense_4h_to_h.weight": "pytorch_model_00004-of-00026.bin",
+    "h.2.mlp.dense_h_to_4h.bias": "pytorch_model_00004-of-00026.bin",
+    "h.2.mlp.dense_h_to_4h.weight": "pytorch_model_00004-of-00026.bin",
+    "h.2.post_attention_layernorm.bias": "pytorch_model_00004-of-00026.bin",
+    "h.2.post_attention_layernorm.weight": "pytorch_model_00004-of-00026.bin",
+    "h.2.self_attention.dense.bias": "pytorch_model_00004-of-00026.bin",
+    "h.2.self_attention.dense.weight": "pytorch_model_00004-of-00026.bin",
+    "h.2.self_attention.query_key_value.bias": "pytorch_model_00004-of-00026.bin",
+    "h.2.self_attention.query_key_value.weight": "pytorch_model_00004-of-00026.bin",
+    "h.20.input_layernorm.bias": "pytorch_model_00022-of-00026.bin",
+    "h.20.input_layernorm.weight": "pytorch_model_00022-of-00026.bin",
+    "h.20.mlp.dense_4h_to_h.bias": "pytorch_model_00022-of-00026.bin",
+    "h.20.mlp.dense_4h_to_h.weight": "pytorch_model_00022-of-00026.bin",
+    "h.20.mlp.dense_h_to_4h.bias": "pytorch_model_00022-of-00026.bin",
+    "h.20.mlp.dense_h_to_4h.weight": "pytorch_model_00022-of-00026.bin",
+    "h.20.post_attention_layernorm.bias": "pytorch_model_00022-of-00026.bin",
+    "h.20.post_attention_layernorm.weight": "pytorch_model_00022-of-00026.bin",
+    "h.20.self_attention.dense.bias": "pytorch_model_00022-of-00026.bin",
+    "h.20.self_attention.dense.weight": "pytorch_model_00022-of-00026.bin",
+    "h.20.self_attention.query_key_value.bias": "pytorch_model_00022-of-00026.bin",
+    "h.20.self_attention.query_key_value.weight": "pytorch_model_00022-of-00026.bin",
+    "h.21.input_layernorm.bias": "pytorch_model_00023-of-00026.bin",
+    "h.21.input_layernorm.weight": "pytorch_model_00023-of-00026.bin",
+    "h.21.mlp.dense_4h_to_h.bias": "pytorch_model_00023-of-00026.bin",
+    "h.21.mlp.dense_4h_to_h.weight": "pytorch_model_00023-of-00026.bin",
+    "h.21.mlp.dense_h_to_4h.bias": "pytorch_model_00023-of-00026.bin",
+    "h.21.mlp.dense_h_to_4h.weight": "pytorch_model_00023-of-00026.bin",
+    "h.21.post_attention_layernorm.bias": "pytorch_model_00023-of-00026.bin",
+    "h.21.post_attention_layernorm.weight": "pytorch_model_00023-of-00026.bin",
+    "h.21.self_attention.dense.bias": "pytorch_model_00023-of-00026.bin",
+    "h.21.self_attention.dense.weight": "pytorch_model_00023-of-00026.bin",
+    "h.21.self_attention.query_key_value.bias": "pytorch_model_00023-of-00026.bin",
+    "h.21.self_attention.query_key_value.weight": "pytorch_model_00023-of-00026.bin",
+    "h.22.input_layernorm.bias": "pytorch_model_00024-of-00026.bin",
+    "h.22.input_layernorm.weight": "pytorch_model_00024-of-00026.bin",
+    "h.22.mlp.dense_4h_to_h.bias": "pytorch_model_00024-of-00026.bin",
+    "h.22.mlp.dense_4h_to_h.weight": "pytorch_model_00024-of-00026.bin",
+    "h.22.mlp.dense_h_to_4h.bias": "pytorch_model_00024-of-00026.bin",
+    "h.22.mlp.dense_h_to_4h.weight": "pytorch_model_00024-of-00026.bin",
+    "h.22.post_attention_layernorm.bias": "pytorch_model_00024-of-00026.bin",
+    "h.22.post_attention_layernorm.weight": "pytorch_model_00024-of-00026.bin",
+    "h.22.self_attention.dense.bias": "pytorch_model_00024-of-00026.bin",
+    "h.22.self_attention.dense.weight": "pytorch_model_00024-of-00026.bin",
+    "h.22.self_attention.query_key_value.bias": "pytorch_model_00024-of-00026.bin",
+    "h.22.self_attention.query_key_value.weight": "pytorch_model_00024-of-00026.bin",
+    "h.23.input_layernorm.bias": "pytorch_model_00025-of-00026.bin",
+    "h.23.input_layernorm.weight": "pytorch_model_00025-of-00026.bin",
+    "h.23.mlp.dense_4h_to_h.bias": "pytorch_model_00025-of-00026.bin",
+    "h.23.mlp.dense_4h_to_h.weight": "pytorch_model_00025-of-00026.bin",
+    "h.23.mlp.dense_h_to_4h.bias": "pytorch_model_00025-of-00026.bin",
+    "h.23.mlp.dense_h_to_4h.weight": "pytorch_model_00025-of-00026.bin",
+    "h.23.post_attention_layernorm.bias": "pytorch_model_00025-of-00026.bin",
+    "h.23.post_attention_layernorm.weight": "pytorch_model_00025-of-00026.bin",
+    "h.23.self_attention.dense.bias": "pytorch_model_00025-of-00026.bin",
+    "h.23.self_attention.dense.weight": "pytorch_model_00025-of-00026.bin",
+    "h.23.self_attention.query_key_value.bias": "pytorch_model_00025-of-00026.bin",
+    "h.23.self_attention.query_key_value.weight": "pytorch_model_00025-of-00026.bin",
+    "h.3.input_layernorm.bias": "pytorch_model_00005-of-00026.bin",
+    "h.3.input_layernorm.weight": "pytorch_model_00005-of-00026.bin",
+    "h.3.mlp.dense_4h_to_h.bias": "pytorch_model_00005-of-00026.bin",
+    "h.3.mlp.dense_4h_to_h.weight": "pytorch_model_00005-of-00026.bin",
+    "h.3.mlp.dense_h_to_4h.bias": "pytorch_model_00005-of-00026.bin",
+    "h.3.mlp.dense_h_to_4h.weight": "pytorch_model_00005-of-00026.bin",
+    "h.3.post_attention_layernorm.bias": "pytorch_model_00005-of-00026.bin",
+    "h.3.post_attention_layernorm.weight": "pytorch_model_00005-of-00026.bin",
+    "h.3.self_attention.dense.bias": "pytorch_model_00005-of-00026.bin",
+    "h.3.self_attention.dense.weight": "pytorch_model_00005-of-00026.bin",
+    "h.3.self_attention.query_key_value.bias": "pytorch_model_00005-of-00026.bin",
+    "h.3.self_attention.query_key_value.weight": "pytorch_model_00005-of-00026.bin",
+    "h.4.input_layernorm.bias": "pytorch_model_00006-of-00026.bin",
+    "h.4.input_layernorm.weight": "pytorch_model_00006-of-00026.bin",
+    "h.4.mlp.dense_4h_to_h.bias": "pytorch_model_00006-of-00026.bin",
+    "h.4.mlp.dense_4h_to_h.weight": "pytorch_model_00006-of-00026.bin",
+    "h.4.mlp.dense_h_to_4h.bias": "pytorch_model_00006-of-00026.bin",
+    "h.4.mlp.dense_h_to_4h.weight": "pytorch_model_00006-of-00026.bin",
+    "h.4.post_attention_layernorm.bias": "pytorch_model_00006-of-00026.bin",
+    "h.4.post_attention_layernorm.weight": "pytorch_model_00006-of-00026.bin",
+    "h.4.self_attention.dense.bias": "pytorch_model_00006-of-00026.bin",
+    "h.4.self_attention.dense.weight": "pytorch_model_00006-of-00026.bin",
+    "h.4.self_attention.query_key_value.bias": "pytorch_model_00006-of-00026.bin",
+    "h.4.self_attention.query_key_value.weight": "pytorch_model_00006-of-00026.bin",
+    "h.5.input_layernorm.bias": "pytorch_model_00007-of-00026.bin",
+    "h.5.input_layernorm.weight": "pytorch_model_00007-of-00026.bin",
+    "h.5.mlp.dense_4h_to_h.bias": "pytorch_model_00007-of-00026.bin",
+    "h.5.mlp.dense_4h_to_h.weight": "pytorch_model_00007-of-00026.bin",
+    "h.5.mlp.dense_h_to_4h.bias": "pytorch_model_00007-of-00026.bin",
+    "h.5.mlp.dense_h_to_4h.weight": "pytorch_model_00007-of-00026.bin",
+    "h.5.post_attention_layernorm.bias": "pytorch_model_00007-of-00026.bin",
+    "h.5.post_attention_layernorm.weight": "pytorch_model_00007-of-00026.bin",
+    "h.5.self_attention.dense.bias": "pytorch_model_00007-of-00026.bin",
+    "h.5.self_attention.dense.weight": "pytorch_model_00007-of-00026.bin",
+    "h.5.self_attention.query_key_value.bias": "pytorch_model_00007-of-00026.bin",
+    "h.5.self_attention.query_key_value.weight": "pytorch_model_00007-of-00026.bin",
+    "h.6.input_layernorm.bias": "pytorch_model_00008-of-00026.bin",
+    "h.6.input_layernorm.weight": "pytorch_model_00008-of-00026.bin",
+    "h.6.mlp.dense_4h_to_h.bias": "pytorch_model_00008-of-00026.bin",
+    "h.6.mlp.dense_4h_to_h.weight": "pytorch_model_00008-of-00026.bin",
+    "h.6.mlp.dense_h_to_4h.bias": "pytorch_model_00008-of-00026.bin",
+    "h.6.mlp.dense_h_to_4h.weight": "pytorch_model_00008-of-00026.bin",
+    "h.6.post_attention_layernorm.bias": "pytorch_model_00008-of-00026.bin",
+    "h.6.post_attention_layernorm.weight": "pytorch_model_00008-of-00026.bin",
+    "h.6.self_attention.dense.bias": "pytorch_model_00008-of-00026.bin",
+    "h.6.self_attention.dense.weight": "pytorch_model_00008-of-00026.bin",
+    "h.6.self_attention.query_key_value.bias": "pytorch_model_00008-of-00026.bin",
+    "h.6.self_attention.query_key_value.weight": "pytorch_model_00008-of-00026.bin",
+    "h.7.input_layernorm.bias": "pytorch_model_00009-of-00026.bin",
+    "h.7.input_layernorm.weight": "pytorch_model_00009-of-00026.bin",
+    "h.7.mlp.dense_4h_to_h.bias": "pytorch_model_00009-of-00026.bin",
+    "h.7.mlp.dense_4h_to_h.weight": "pytorch_model_00009-of-00026.bin",
+    "h.7.mlp.dense_h_to_4h.bias": "pytorch_model_00009-of-00026.bin",
+    "h.7.mlp.dense_h_to_4h.weight": "pytorch_model_00009-of-00026.bin",
+    "h.7.post_attention_layernorm.bias": "pytorch_model_00009-of-00026.bin",
+    "h.7.post_attention_layernorm.weight": "pytorch_model_00009-of-00026.bin",
+    "h.7.self_attention.dense.bias": "pytorch_model_00009-of-00026.bin",
+    "h.7.self_attention.dense.weight": "pytorch_model_00009-of-00026.bin",
+    "h.7.self_attention.query_key_value.bias": "pytorch_model_00009-of-00026.bin",
+    "h.7.self_attention.query_key_value.weight": "pytorch_model_00009-of-00026.bin",
+    "h.8.input_layernorm.bias": "pytorch_model_00010-of-00026.bin",
+    "h.8.input_layernorm.weight": "pytorch_model_00010-of-00026.bin",
+    "h.8.mlp.dense_4h_to_h.bias": "pytorch_model_00010-of-00026.bin",
+    "h.8.mlp.dense_4h_to_h.weight": "pytorch_model_00010-of-00026.bin",
+    "h.8.mlp.dense_h_to_4h.bias": "pytorch_model_00010-of-00026.bin",
+    "h.8.mlp.dense_h_to_4h.weight": "pytorch_model_00010-of-00026.bin",
+    "h.8.post_attention_layernorm.bias": "pytorch_model_00010-of-00026.bin",
+    "h.8.post_attention_layernorm.weight": "pytorch_model_00010-of-00026.bin",
+    "h.8.self_attention.dense.bias": "pytorch_model_00010-of-00026.bin",
+    "h.8.self_attention.dense.weight": "pytorch_model_00010-of-00026.bin",
+    "h.8.self_attention.query_key_value.bias": "pytorch_model_00010-of-00026.bin",
+    "h.8.self_attention.query_key_value.weight": "pytorch_model_00010-of-00026.bin",
+    "h.9.input_layernorm.bias": "pytorch_model_00011-of-00026.bin",
+    "h.9.input_layernorm.weight": "pytorch_model_00011-of-00026.bin",
+    "h.9.mlp.dense_4h_to_h.bias": "pytorch_model_00011-of-00026.bin",
+    "h.9.mlp.dense_4h_to_h.weight": "pytorch_model_00011-of-00026.bin",
+    "h.9.mlp.dense_h_to_4h.bias": "pytorch_model_00011-of-00026.bin",
+    "h.9.mlp.dense_h_to_4h.weight": "pytorch_model_00011-of-00026.bin",
+    "h.9.post_attention_layernorm.bias": "pytorch_model_00011-of-00026.bin",
+    "h.9.post_attention_layernorm.weight": "pytorch_model_00011-of-00026.bin",
+    "h.9.self_attention.dense.bias": "pytorch_model_00011-of-00026.bin",
+    "h.9.self_attention.dense.weight": "pytorch_model_00011-of-00026.bin",
+    "h.9.self_attention.query_key_value.bias": "pytorch_model_00011-of-00026.bin",
+    "h.9.self_attention.query_key_value.weight": "pytorch_model_00011-of-00026.bin",
+    "ln_f.bias": "pytorch_model_00026-of-00026.bin",
+    "ln_f.weight": "pytorch_model_00026-of-00026.bin",
+    "word_embeddings.weight": "pytorch_model_00001-of-00026.bin",
+    "word_embeddings_layernorm.bias": "pytorch_model_00001-of-00026.bin",
+    "word_embeddings_layernorm.weight": "pytorch_model_00001-of-00026.bin"
+  }
+}

pytorch_model_00001-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc73b4a208404b01da1eabd2667a720b49b428534bfcb97fd403eab3980cf9d7
+size 770711527

pytorch_model_00002-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6fc1efc151ac025aaec657c02e05dd1e8683544c041fd6d2d6b441e17bf798
+size 56667778

pytorch_model_00003-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d552aba533de65b990d9f01ad2e2eceb61959395174d0d4ddc53442b31ff995e
+size 56667778

pytorch_model_00004-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d6e50b119e295c31589bd915cb240ada412bba1a116df8493b8cf761739d21
+size 56667778

pytorch_model_00005-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572ddfb49d0a81c591dafe05a5aa9e2e5eba6615302fa7d33f1c3ad610b40312
+size 56667778

pytorch_model_00006-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9bfcdd71e0d9bb4b0b8d7cdb1a6e79b3938beaf39295f3bf259bc5a0745503
+size 56667778

pytorch_model_00007-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd2563300c1eb8210ada0c6c2ba5f43a253466a90a669501c194519116ac594
+size 56667778

pytorch_model_00008-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ddc95be16fed815e3a0591eab5a01483860d2c7494b750fe59826092badc2f5
+size 56667778

pytorch_model_00009-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8ae9baf01ae10b61dc0ce653833aac2ab70c64497ba40203beb538efcb6f25
+size 56667778

pytorch_model_00010-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a37b714fd5137aeb8743960866c2ce688d2ec92d8f8ff781611ffbcb84691ae
+size 56667778

pytorch_model_00011-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13bc46d2b9dcb86137081651359bcdcf9f48bc1fa04ed30cc7fce80090034b6
+size 56667778

pytorch_model_00012-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cad596338757ab5ec4be1171767e34edba24855f48638c4c61e1924f4e78c85
+size 56667778

pytorch_model_00013-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee19c6e7365e09d8457cb7257ce48c3dac2fbbd21dddb83f11598425e1fbf5e5
+size 56667778

pytorch_model_00014-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89336fd6e6fd59c03dec6754d068833c0f2987383923930e29c7e88c3f7d0a06
+size 56667778

pytorch_model_00015-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5eceff01c1cea0f00de992b4776da5b68101078c9a75fc7c63117a8d0226f7
+size 56667778

pytorch_model_00016-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80dff1d94ae89e7e4a3e32cf508c5a152206575a5968e3557d60e2b9807fb9fa
+size 56667778

pytorch_model_00017-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c45489c0a48371e4e90dc8d1bae9da0a3e92bde10c03c5413f4e1e4ef293a83
+size 56667778

pytorch_model_00018-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a74987e4e7d9c3a91f3153585de04bfececa0539851b4c49cfdc7558566722
+size 56667778

pytorch_model_00019-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef27ad2ac0fde596e992901326302438870b7c3334028ba1d30f46a39ccdf9df
+size 56667778

pytorch_model_00020-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17ae508ca43c55f83ba14fab1d620f5f0286f5b909b3f4f1f082c934e12a15d
+size 56667778

pytorch_model_00021-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f327c005f4f49ad35460aac760ea0908211480254e20206a8836720aeef709e6
+size 56667778