Upload model

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/home/ext_u10bei_github_io_gmail_com/ucllm_nedo_dev/train/output/step3_upload_pretrained_model/gpt_6.7B_global_step6600",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 59648,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 59648,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 4096,
+  "n_head": 32,
+  "n_inner": 16384,
+  "n_layer": 32,
+  "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": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 59648
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 59648,
+  "eos_token_id": 59648,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b31186a5e50e09ba2074dcf65590938ae52ed2cee86b581aa729becd8ad2244
+size 4769978512

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e1d314d40a5fcf56e86c898954b9d273e758411183eccd5abed1e1e7e89aa6
+size 4833123736

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ed10978ba46d3249263da093d9e890d3199b5b28a3f7344a31a37cace6b22d
+size 4833123800

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033fbfb6e52bfa8f19bcfa88ff83da24743b019abc58523f00e277ea0b43e0f1
+size 4833123800

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14839b754fb77d2a3172d48becf6220ead10b804bd6671b503edca9e42105e41
+size 4833123800

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ffe6e1a7f0aedffcccfa6c0d2785b7e68716e2d8d6df4fc2e5a4b6c66c53f2
+size 2685046912

model.safetensors.index.json

@@ -0,0 +1,395 @@
+{
+  "metadata": {
+    "total_size": 26787479552
+  },
+  "weight_map": {
+    "transformer.h.0.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.10.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_attn.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_attn.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_proj.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.attn.c_proj.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00003-of-00006.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.2.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.20.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.attn.c_attn.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.attn.c_attn.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.attn.c_proj.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.attn.c_proj.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00004-of-00006.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.24.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.25.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.26.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.27.mlp.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.attn.c_attn.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.attn.c_attn.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.attn.c_proj.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.attn.c_proj.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.ln_1.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.ln_1.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.ln_2.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.ln_2.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.mlp.c_fc.bias": "model-00005-of-00006.safetensors",
+    "transformer.h.28.mlp.c_fc.weight": "model-00005-of-00006.safetensors",
+    "transformer.h.28.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.28.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.attn.c_attn.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.attn.c_attn.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.attn.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.attn.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.ln_1.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.ln_1.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.ln_2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.ln_2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.29.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.3.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.30.attn.c_attn.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.attn.c_attn.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.attn.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.attn.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.ln_1.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.ln_1.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.ln_2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.ln_2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.30.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.30.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.attn.c_attn.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.attn.c_attn.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.attn.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.attn.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.ln_1.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.ln_1.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.ln_2.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.ln_2.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.mlp.c_fc.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.mlp.c_fc.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.31.mlp.c_proj.bias": "model-00006-of-00006.safetensors",
+    "transformer.h.31.mlp.c_proj.weight": "model-00006-of-00006.safetensors",
+    "transformer.h.4.attn.c_attn.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.attn.c_attn.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.attn.c_proj.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.attn.c_proj.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00006.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_attn.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_attn.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.attn.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00002-of-00006.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00006.safetensors",
+    "transformer.ln_f.bias": "model-00006-of-00006.safetensors",
+    "transformer.ln_f.weight": "model-00006-of-00006.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00006.safetensors",
+    "transformer.wte.weight": "model-00001-of-00006.safetensors"
+  }
+}