Upload 12 files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 7,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 7,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": 20480,
+  "n_layer": 40,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 50688
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 7,
+  "eos_token_id": 7,
+  "transformers_version": "4.34.0"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c71a7ecddb3bcc21065116072115fb617c56f6e80637996474e17109c37647
+size 9890006847

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4bcdaffda1f3a5426b58dc552020e3e6c804ef0874c444d306114a07d2977f
+size 9648999451

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1a66c81c65fa32f5123741ebb473d37bf3a780f94cee0054450ea16038e5b4
+size 9648979767

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfdfcf60189b42eeed4d02e48f40a3286dc87caaefdf78044689bc4932b5c43
+size 9963572323

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98a9d2f1361647a9cd7593b1198175af3b0f707fba951d9310d4da336061995c
+size 9753857823

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a06b4e660d2e0596075d5f332cc200df9d0ea976b27420cdfe9503044d29c6b
+size 2517123007

pytorch_model.bin.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_size": 51422371840
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.10.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.20.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.30.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "transformer.h.30.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "transformer.h.38.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_1.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_1.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.h.7.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "transformer.ln_f.bias": "pytorch_model-00006-of-00006.bin",
+    "transformer.ln_f.weight": "pytorch_model-00006-of-00006.bin",
+    "transformer.wpe.weight": "pytorch_model-00001-of-00006.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": [
+    "</s|LLM-jp>"
+  ],
+  "bos_token": "<s|LLM-jp>",
+  "cls_token": "<CLS|LLM-jp>",
+  "eos_token": "<EOD|LLM-jp>",
+  "mask_token": "<mask|LLM-jp>",
+  "pad_token": "<unk|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "unk_token": "<unk|LLM-jp>"
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<mask|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<pad|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "</s|LLM-jp>"
+  ],
+  "bos_token": "<s|LLM-jp>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "<EOD|LLM-jp>",
+  "eos_token": "<EOD|LLM-jp>",
+  "extra_ids": 0,
+  "mask_token": "<mask|LLM-jp>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk|LLM-jp>",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk|LLM-jp>"
+}