Upload RWForCausalLM

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
+    "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.0.dev0"
+}

pytorch_model-00001-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed44e98a5642e6f86475084bfa0cef8a1a482b655e22a0b428d021d623911583
+size 1679792127

pytorch_model-00002-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4937982f478ace49d7f306d523c5bd84c9104b3fbdd2e788df79e7185332edb5
+size 1986969437

pytorch_model-00003-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24451521d75be8c5a48a7995c18d1ea5a08785a61431d3a882fc4744ee90a302
+size 1824075851

pytorch_model-00004-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af0d6bf5c7312c9d196ecac9cc2afec1fa8b9132e55025fa829cc03a9d0690d
+size 1986932473

pytorch_model-00005-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0f5d716c73b61277bcf151bb9fb456a5e4d5419b8090e1654cdf9f2835b08a
+size 1986969437

pytorch_model-00006-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba52ca2eb015f4e8902866bd9e704f6ecf1843ec514591afcb94edea3766ab3d
+size 1824075851

pytorch_model-00007-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17637d7fb2674cd505ff2286050d649411ae8b85979738325abf56ee167754e
+size 1986932473

pytorch_model-00008-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d726249bfd514234a02037d84a8b4d9a7f4260192b9f9ada58915539d0ae465
+size 1986969501

pytorch_model-00009-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72e7f5f01a3609ea6a8d730b0dd08c00159e447ec5423f270dbf2327d0fffba
+size 1824075851

pytorch_model-00010-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa9c7af3743584744dc017ceea574ae3d77ed9ba065ad686dc1cf083e0fcec5
+size 1986932473

pytorch_model-00011-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1c87a8012d2fa257d2beda1c9e6d49bd59ae3fe1ed2992122a56532d4d1ca
+size 1986969501

pytorch_model-00012-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7359a887641b69e0859c919136505d4b8e1bde062a0bb74136892f7a57302d2
+size 1824075851

pytorch_model-00013-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07a593943ecb6dd1f52ec07de89c9ebc2496ecdb7763f990405686eafb0e334
+size 1986932473

pytorch_model-00014-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04aa4621869954a2068afef9d9034b3f41157c022b8cd35f0c2b9a9ebd87147d
+size 1986969501

pytorch_model-00015-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee51c6994308999d9f082ad74ae2b43cc759a0d62f13e49234315c19b3a72e09
+size 828282879

pytorch_model-00016-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0381d187885ccfefdb47aa5d244dc61afbd2acd1a9accabcce543f7172de8f8b
+size 1181877162

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 28868759040
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00016-of-00016.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00016.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00016.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00016.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00016.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00016.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00006-of-00016.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00007-of-00016.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00009-of-00016.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00010-of-00016.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00012-of-00016.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00013-of-00016.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00016.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00016.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00015-of-00016.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00015-of-00016.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00016.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00016.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00016.bin",
+    "transformer.ln_f.bias": "pytorch_model-00015-of-00016.bin",
+    "transformer.ln_f.weight": "pytorch_model-00015-of-00016.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00016.bin"
+  }
+}