Add Polyglot-ko 12.8B model converted to Int8 & Safetensors

.gitignore

@@ -0,0 +1,189 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,jupyternotebooks
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,jupyternotebooks
+
+### JupyterNotebooks ###
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+
+# IPython
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python,jupyternotebooks
+*.ipynb
+

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "EleutherAI/polyglot-ko-12.8b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_steps": "global_step301000",
+  "quantization_config": {
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_8bit": true
+  },
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.29.2"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69383f9bfd96b9c8caa7d84f78194f4fba6d68b1e003b5e2b77f8a896871d5f6
+size 950428958

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4641f3bc921f68bac15c5a6ed7806fdbfa5d5fbb6ba618e7964e78d5556f01f1
+size 957260110

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121ced21e975eef1c7b35a4232fc78ad1a7b6fc9f6ff9a10bc7272aa865d62c1
+size 957260110

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949fdd1e6682b59dec195b8aa9052f26d77eee8b0e0d15b76fecf825ddf7951f
+size 957260134

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12a56df98f03d33e3b927a9cac1378516f2aece2f577009dd8b3ac1ec5ef995
+size 957260166

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fde4977939068b952e237c72313f49c2f2a108898d27ac785ef58b9ff5b614e
+size 957260166

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6689a82d2ac1789c731db88d513463cde4220d266bebeef19235cdf825ccf69
+size 957260166

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dd59c702c467c0f24accfb235139c634d289a9b373756988d9cfaf08c387c5
+size 957260166

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe63049f755758490b2d5d89d444266132f70a7c7de0f7ceb434ae46d1d0e10e
+size 957260166

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae6098afdf945a0dc22b985d1901edee949cfdd1576dad1336fba687b7c8582
+size 957260166

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd27b5ffd708135bf6bdf7904365984bef840d174eeff9828470108d5800c70
+size 957260166

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5055f40da9072a6ce33fa0cd8906d523ef3d6f77f0358c07953854b037ba74ef
+size 957260166

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9281169e28dee7e1cb790067e75c15244ac40e7e65f587675a2895ce9658d180
+size 957260166

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8b600b35edd4a0680e6b9b87afca332972114b1a54d15dad228a8683b6e8ba
+size 941977426

model.safetensors.index.json

@@ -0,0 +1,771 @@
+{
+  "metadata": {
+    "total_size": 13379443280
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.dense.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.dense.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.SCB": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.dense.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.masked_bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.dense.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.masked_bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.dense.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.masked_bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.dense.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.masked_bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.SCB": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.dense.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.masked_bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.dense.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.masked_bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.dense.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.masked_bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.SCB": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.dense.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.masked_bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.dense.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.masked_bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.dense.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.masked_bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.SCB": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.dense.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.masked_bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.dense.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.masked_bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.dense.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.masked_bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.dense.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.masked_bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.SCB": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.dense.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.masked_bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.dense.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.dense.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.dense.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.masked_bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.input_layernorm.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.dense.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.dense.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.dense.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.masked_bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.input_layernorm.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.SCB": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.dense.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.dense.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.dense.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.masked_bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.input_layernorm.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.dense.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.dense.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.dense.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.masked_bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.input_layernorm.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.dense.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.dense.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.dense.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.masked_bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.input_layernorm.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.SCB": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.dense.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.dense.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.dense.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.masked_bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.input_layernorm.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.dense.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.masked_bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.dense.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.dense.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.dense.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.masked_bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.input_layernorm.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.dense.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.dense.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.dense.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.masked_bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.input_layernorm.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.SCB": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.dense.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.dense.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.dense.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.masked_bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.input_layernorm.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.dense.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.dense.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.dense.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.masked_bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.input_layernorm.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.dense.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.dense.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.dense.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.masked_bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.input_layernorm.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.SCB": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.dense.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.dense.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.dense.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.masked_bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.input_layernorm.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.dense.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.dense.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.dense.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.masked_bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.query_key_value.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.input_layernorm.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.dense.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.dense.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.dense.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.masked_bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.query_key_value.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.input_layernorm.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.SCB": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.dense.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.dense.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.dense.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.masked_bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.query_key_value.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.input_layernorm.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.dense.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.dense.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.dense.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.masked_bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.query_key_value.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.input_layernorm.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.SCB": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.dense.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.masked_bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.SCB": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.dense.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.masked_bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.dense.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.masked_bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.dense.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.masked_bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.SCB": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.dense.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.masked_bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.dense.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.masked_bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.SCB": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}