Upload RWForCausalLM

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "ehartford/WizardLM-Uncensored-Falcon-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "ehartford/WizardLM-Uncensored-Falcon-7b--configuration_RW.RWConfig",
+    "AutoModelForCausalLM": "ehartford/WizardLM-Uncensored-Falcon-7b--modelling_RW.RWForCausalLM"
+  },
+  "bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": "bfloat16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65025
+}

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-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748a30c8d1a9de5c00bcf286ff8cb52514e5877559b8569c1c05438b72f0b98d
+size 839906431

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d64890f60c37100f8ef1807c93090edefe174a73c0dabedf3fd729d85c4a789
+size 993487325

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8628bd12230d7f972ff23d3cf4ea0b66aac7fa52549e3fc6d3326537ca94215c
+size 912040395

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04809ec237181a29bd95cfec4e5ba2dda22ce4ee83002ee7fa2dc8d5885e6ee3
+size 993468537

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabe7c666d7fd2ba3aa84bf8433dcc08c221e8a817c71c722ab44e69605a8a9a
+size 993487325

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38766c2abc31dcec29a568450640f225d8431bf4fe5b07d509f6b6f105f7f61
+size 912040395

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6d00385cebb44d32b5df4750009c2c5759636a2ee3be8b2f6846b571bb4f6c
+size 993468537

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fb7a934ee1d4a99be1349a5d82b399fb05d1dd4ed9f13ca14433e524d6f62a
+size 993487325

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc642e60a29d9d5f2f1bbf66fcc195ff131aea7bc1a2b90f6fa55b009b90941a
+size 912040395

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863c945e225cd904dc5ecf860efa4404393b49d269e8920652c827c2b6d4048a
+size 993468537

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:817da570eb6f53be990ed184e1fe48ea403bceacfd576d595cc43c12ebfb26c0
+size 993487325

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac4409f26b7a5e95841ab005b62dd26d9ca0d905170ddafd1e78315efbea330
+size 912040395

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea122e3c35fe72ffe2fb72de0e31e39a9e9d6f5ef0e1df7f9d1ae243273898e8
+size 993468537

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3152205e8b6da73e0ec2acf0c10844c1fdcd655672497cf6b3f8d6b01c8c5a5a
+size 993487325

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8294d7d0fb594eecbca811c0b6b8a75b1b4f221aeb42a3f1dc9eb4111bcbac4e
+size 414142655

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 13843450496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00015.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00015.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00015.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00015.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00015.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00015-of-00015.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00015-of-00015.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00015-of-00015.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
+    "transformer.ln_f.bias": "pytorch_model-00015-of-00015.bin",
+    "transformer.ln_f.weight": "pytorch_model-00015-of-00015.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00015.bin"
+  }
+}