beomi commited on
Commit
309c6bd
1 Parent(s): 9413188

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

Browse files
.gitignore ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Created by https://www.toptal.com/developers/gitignore/api/python,jupyternotebooks
2
+ # Edit at https://www.toptal.com/developers/gitignore?templates=python,jupyternotebooks
3
+
4
+ ### JupyterNotebooks ###
5
+ # gitignore template for Jupyter Notebooks
6
+ # website: http://jupyter.org/
7
+
8
+ .ipynb_checkpoints
9
+ */.ipynb_checkpoints/*
10
+
11
+ # IPython
12
+ profile_default/
13
+ ipython_config.py
14
+
15
+ # Remove previous ipynb_checkpoints
16
+ # git rm -r .ipynb_checkpoints/
17
+
18
+ ### Python ###
19
+ # Byte-compiled / optimized / DLL files
20
+ __pycache__/
21
+ *.py[cod]
22
+ *$py.class
23
+
24
+ # C extensions
25
+ *.so
26
+
27
+ # Distribution / packaging
28
+ .Python
29
+ build/
30
+ develop-eggs/
31
+ dist/
32
+ downloads/
33
+ eggs/
34
+ .eggs/
35
+ lib/
36
+ lib64/
37
+ parts/
38
+ sdist/
39
+ var/
40
+ wheels/
41
+ share/python-wheels/
42
+ *.egg-info/
43
+ .installed.cfg
44
+ *.egg
45
+ MANIFEST
46
+
47
+ # PyInstaller
48
+ # Usually these files are written by a python script from a template
49
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
50
+ *.manifest
51
+ *.spec
52
+
53
+ # Installer logs
54
+ pip-log.txt
55
+ pip-delete-this-directory.txt
56
+
57
+ # Unit test / coverage reports
58
+ htmlcov/
59
+ .tox/
60
+ .nox/
61
+ .coverage
62
+ .coverage.*
63
+ .cache
64
+ nosetests.xml
65
+ coverage.xml
66
+ *.cover
67
+ *.py,cover
68
+ .hypothesis/
69
+ .pytest_cache/
70
+ cover/
71
+
72
+ # Translations
73
+ *.mo
74
+ *.pot
75
+
76
+ # Django stuff:
77
+ *.log
78
+ local_settings.py
79
+ db.sqlite3
80
+ db.sqlite3-journal
81
+
82
+ # Flask stuff:
83
+ instance/
84
+ .webassets-cache
85
+
86
+ # Scrapy stuff:
87
+ .scrapy
88
+
89
+ # Sphinx documentation
90
+ docs/_build/
91
+
92
+ # PyBuilder
93
+ .pybuilder/
94
+ target/
95
+
96
+ # Jupyter Notebook
97
+
98
+ # IPython
99
+
100
+ # pyenv
101
+ # For a library or package, you might want to ignore these files since the code is
102
+ # intended to run in multiple environments; otherwise, check them in:
103
+ # .python-version
104
+
105
+ # pipenv
106
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
107
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
108
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
109
+ # install all needed dependencies.
110
+ #Pipfile.lock
111
+
112
+ # poetry
113
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
114
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
115
+ # commonly ignored for libraries.
116
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
117
+ #poetry.lock
118
+
119
+ # pdm
120
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
121
+ #pdm.lock
122
+ # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
123
+ # in version control.
124
+ # https://pdm.fming.dev/#use-with-ide
125
+ .pdm.toml
126
+
127
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
128
+ __pypackages__/
129
+
130
+ # Celery stuff
131
+ celerybeat-schedule
132
+ celerybeat.pid
133
+
134
+ # SageMath parsed files
135
+ *.sage.py
136
+
137
+ # Environments
138
+ .env
139
+ .venv
140
+ env/
141
+ venv/
142
+ ENV/
143
+ env.bak/
144
+ venv.bak/
145
+
146
+ # Spyder project settings
147
+ .spyderproject
148
+ .spyproject
149
+
150
+ # Rope project settings
151
+ .ropeproject
152
+
153
+ # mkdocs documentation
154
+ /site
155
+
156
+ # mypy
157
+ .mypy_cache/
158
+ .dmypy.json
159
+ dmypy.json
160
+
161
+ # Pyre type checker
162
+ .pyre/
163
+
164
+ # pytype static type analyzer
165
+ .pytype/
166
+
167
+ # Cython debug symbols
168
+ cython_debug/
169
+
170
+ # PyCharm
171
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
172
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
173
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
174
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
175
+ #.idea/
176
+
177
+ ### Python Patch ###
178
+ # Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
179
+ poetry.toml
180
+
181
+ # ruff
182
+ .ruff_cache/
183
+
184
+ # LSP config files
185
+ pyrightconfig.json
186
+
187
+ # End of https://www.toptal.com/developers/gitignore/api/python,jupyternotebooks
188
+ *.ipynb
189
+
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/polyglot-ko-12.8b",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_steps": "global_step301000",
19
+ "quantization_config": {
20
+ "llm_int8_enable_fp32_cpu_offload": false,
21
+ "llm_int8_skip_modules": null,
22
+ "llm_int8_threshold": 6.0,
23
+ "load_in_8bit": true
24
+ },
25
+ "rotary_emb_base": 10000,
26
+ "rotary_pct": 0.5,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.29.2",
30
+ "use_cache": true,
31
+ "use_parallel_residual": true,
32
+ "vocab_size": 30080
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.29.2"
6
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69383f9bfd96b9c8caa7d84f78194f4fba6d68b1e003b5e2b77f8a896871d5f6
3
+ size 950428958
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4641f3bc921f68bac15c5a6ed7806fdbfa5d5fbb6ba618e7964e78d5556f01f1
3
+ size 957260110
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121ced21e975eef1c7b35a4232fc78ad1a7b6fc9f6ff9a10bc7272aa865d62c1
3
+ size 957260110
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949fdd1e6682b59dec195b8aa9052f26d77eee8b0e0d15b76fecf825ddf7951f
3
+ size 957260134
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12a56df98f03d33e3b927a9cac1378516f2aece2f577009dd8b3ac1ec5ef995
3
+ size 957260166
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fde4977939068b952e237c72313f49c2f2a108898d27ac785ef58b9ff5b614e
3
+ size 957260166
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6689a82d2ac1789c731db88d513463cde4220d266bebeef19235cdf825ccf69
3
+ size 957260166
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21dd59c702c467c0f24accfb235139c634d289a9b373756988d9cfaf08c387c5
3
+ size 957260166
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe63049f755758490b2d5d89d444266132f70a7c7de0f7ceb434ae46d1d0e10e
3
+ size 957260166
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae6098afdf945a0dc22b985d1901edee949cfdd1576dad1336fba687b7c8582
3
+ size 957260166
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd27b5ffd708135bf6bdf7904365984bef840d174eeff9828470108d5800c70
3
+ size 957260166
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5055f40da9072a6ce33fa0cd8906d523ef3d6f77f0358c07953854b037ba74ef
3
+ size 957260166
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9281169e28dee7e1cb790067e75c15244ac40e7e65f587675a2895ce9658d180
3
+ size 957260166
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8b600b35edd4a0680e6b9b87afca332972114b1a54d15dad228a8683b6e8ba
3
+ size 941977426
model.safetensors.index.json ADDED
@@ -0,0 +1,771 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13379443280
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00014-of-00014.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00014.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00014-of-00014.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00014-of-00014.safetensors",
10
+ "gpt_neox.layers.0.attention.bias": "model-00001-of-00014.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.SCB": "model-00001-of-00014.safetensors",
12
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00014.safetensors",
13
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00014.safetensors",
14
+ "gpt_neox.layers.0.attention.masked_bias": "model-00001-of-00014.safetensors",
15
+ "gpt_neox.layers.0.attention.query_key_value.SCB": "model-00001-of-00014.safetensors",
16
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00014.safetensors",
17
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00014.safetensors",
18
+ "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
19
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00014.safetensors",
20
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.SCB": "model-00001-of-00014.safetensors",
22
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00014.safetensors",
23
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00014.safetensors",
24
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.SCB": "model-00001-of-00014.safetensors",
25
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00014.safetensors",
26
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00014.safetensors",
27
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
28
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
29
+ "gpt_neox.layers.1.attention.bias": "model-00001-of-00014.safetensors",
30
+ "gpt_neox.layers.1.attention.dense.SCB": "model-00001-of-00014.safetensors",
31
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00014.safetensors",
32
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00014.safetensors",
33
+ "gpt_neox.layers.1.attention.masked_bias": "model-00001-of-00014.safetensors",
34
+ "gpt_neox.layers.1.attention.query_key_value.SCB": "model-00001-of-00014.safetensors",
35
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00014.safetensors",
36
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00014.safetensors",
37
+ "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
38
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00014.safetensors",
39
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
40
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.SCB": "model-00001-of-00014.safetensors",
41
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00014.safetensors",
42
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00014.safetensors",
43
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.SCB": "model-00001-of-00014.safetensors",
44
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00014.safetensors",
45
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00014.safetensors",
46
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
47
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
48
+ "gpt_neox.layers.10.attention.bias": "model-00004-of-00014.safetensors",
49
+ "gpt_neox.layers.10.attention.dense.SCB": "model-00004-of-00014.safetensors",
50
+ "gpt_neox.layers.10.attention.dense.bias": "model-00004-of-00014.safetensors",
51
+ "gpt_neox.layers.10.attention.dense.weight": "model-00004-of-00014.safetensors",
52
+ "gpt_neox.layers.10.attention.masked_bias": "model-00004-of-00014.safetensors",
53
+ "gpt_neox.layers.10.attention.query_key_value.SCB": "model-00004-of-00014.safetensors",
54
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00004-of-00014.safetensors",
55
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00004-of-00014.safetensors",
56
+ "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
57
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00004-of-00014.safetensors",
58
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
59
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.SCB": "model-00004-of-00014.safetensors",
60
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
61
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
62
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.SCB": "model-00004-of-00014.safetensors",
63
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
64
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
65
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
66
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
67
+ "gpt_neox.layers.11.attention.bias": "model-00004-of-00014.safetensors",
68
+ "gpt_neox.layers.11.attention.dense.SCB": "model-00005-of-00014.safetensors",
69
+ "gpt_neox.layers.11.attention.dense.bias": "model-00005-of-00014.safetensors",
70
+ "gpt_neox.layers.11.attention.dense.weight": "model-00005-of-00014.safetensors",
71
+ "gpt_neox.layers.11.attention.masked_bias": "model-00004-of-00014.safetensors",
72
+ "gpt_neox.layers.11.attention.query_key_value.SCB": "model-00005-of-00014.safetensors",
73
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00005-of-00014.safetensors",
74
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00005-of-00014.safetensors",
75
+ "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
76
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00004-of-00014.safetensors",
77
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
78
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.SCB": "model-00005-of-00014.safetensors",
79
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
80
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
81
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.SCB": "model-00005-of-00014.safetensors",
82
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
83
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
84
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
85
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
86
+ "gpt_neox.layers.12.attention.bias": "model-00005-of-00014.safetensors",
87
+ "gpt_neox.layers.12.attention.dense.SCB": "model-00005-of-00014.safetensors",
88
+ "gpt_neox.layers.12.attention.dense.bias": "model-00005-of-00014.safetensors",
89
+ "gpt_neox.layers.12.attention.dense.weight": "model-00005-of-00014.safetensors",
90
+ "gpt_neox.layers.12.attention.masked_bias": "model-00005-of-00014.safetensors",
91
+ "gpt_neox.layers.12.attention.query_key_value.SCB": "model-00005-of-00014.safetensors",
92
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00005-of-00014.safetensors",
93
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00005-of-00014.safetensors",
94
+ "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
95
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00005-of-00014.safetensors",
96
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
97
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.SCB": "model-00005-of-00014.safetensors",
98
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
99
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
100
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.SCB": "model-00005-of-00014.safetensors",
101
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
102
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
103
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
104
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
105
+ "gpt_neox.layers.13.attention.bias": "model-00005-of-00014.safetensors",
106
+ "gpt_neox.layers.13.attention.dense.SCB": "model-00005-of-00014.safetensors",
107
+ "gpt_neox.layers.13.attention.dense.bias": "model-00005-of-00014.safetensors",
108
+ "gpt_neox.layers.13.attention.dense.weight": "model-00005-of-00014.safetensors",
109
+ "gpt_neox.layers.13.attention.masked_bias": "model-00005-of-00014.safetensors",
110
+ "gpt_neox.layers.13.attention.query_key_value.SCB": "model-00005-of-00014.safetensors",
111
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00005-of-00014.safetensors",
112
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00005-of-00014.safetensors",
113
+ "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
114
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00005-of-00014.safetensors",
115
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
116
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.SCB": "model-00005-of-00014.safetensors",
117
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
118
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
119
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.SCB": "model-00005-of-00014.safetensors",
120
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
121
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
122
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
123
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
124
+ "gpt_neox.layers.14.attention.bias": "model-00005-of-00014.safetensors",
125
+ "gpt_neox.layers.14.attention.dense.SCB": "model-00006-of-00014.safetensors",
126
+ "gpt_neox.layers.14.attention.dense.bias": "model-00006-of-00014.safetensors",
127
+ "gpt_neox.layers.14.attention.dense.weight": "model-00006-of-00014.safetensors",
128
+ "gpt_neox.layers.14.attention.masked_bias": "model-00005-of-00014.safetensors",
129
+ "gpt_neox.layers.14.attention.query_key_value.SCB": "model-00006-of-00014.safetensors",
130
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00006-of-00014.safetensors",
131
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00006-of-00014.safetensors",
132
+ "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
133
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00005-of-00014.safetensors",
134
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00005-of-00014.safetensors",
135
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.SCB": "model-00006-of-00014.safetensors",
136
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
137
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
138
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.SCB": "model-00006-of-00014.safetensors",
139
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
140
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
141
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
142
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
143
+ "gpt_neox.layers.15.attention.bias": "model-00006-of-00014.safetensors",
144
+ "gpt_neox.layers.15.attention.dense.SCB": "model-00006-of-00014.safetensors",
145
+ "gpt_neox.layers.15.attention.dense.bias": "model-00006-of-00014.safetensors",
146
+ "gpt_neox.layers.15.attention.dense.weight": "model-00006-of-00014.safetensors",
147
+ "gpt_neox.layers.15.attention.masked_bias": "model-00006-of-00014.safetensors",
148
+ "gpt_neox.layers.15.attention.query_key_value.SCB": "model-00006-of-00014.safetensors",
149
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00006-of-00014.safetensors",
150
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00006-of-00014.safetensors",
151
+ "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
152
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00006-of-00014.safetensors",
153
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
154
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.SCB": "model-00006-of-00014.safetensors",
155
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
156
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
157
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.SCB": "model-00006-of-00014.safetensors",
158
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
159
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
160
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
161
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
162
+ "gpt_neox.layers.16.attention.bias": "model-00006-of-00014.safetensors",
163
+ "gpt_neox.layers.16.attention.dense.SCB": "model-00006-of-00014.safetensors",
164
+ "gpt_neox.layers.16.attention.dense.bias": "model-00006-of-00014.safetensors",
165
+ "gpt_neox.layers.16.attention.dense.weight": "model-00006-of-00014.safetensors",
166
+ "gpt_neox.layers.16.attention.masked_bias": "model-00006-of-00014.safetensors",
167
+ "gpt_neox.layers.16.attention.query_key_value.SCB": "model-00006-of-00014.safetensors",
168
+ "gpt_neox.layers.16.attention.query_key_value.bias": "model-00006-of-00014.safetensors",
169
+ "gpt_neox.layers.16.attention.query_key_value.weight": "model-00006-of-00014.safetensors",
170
+ "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
171
+ "gpt_neox.layers.16.input_layernorm.bias": "model-00006-of-00014.safetensors",
172
+ "gpt_neox.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
173
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.SCB": "model-00006-of-00014.safetensors",
174
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
175
+ "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
176
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.SCB": "model-00006-of-00014.safetensors",
177
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
178
+ "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
179
+ "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
180
+ "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
181
+ "gpt_neox.layers.17.attention.bias": "model-00006-of-00014.safetensors",
182
+ "gpt_neox.layers.17.attention.dense.SCB": "model-00007-of-00014.safetensors",
183
+ "gpt_neox.layers.17.attention.dense.bias": "model-00007-of-00014.safetensors",
184
+ "gpt_neox.layers.17.attention.dense.weight": "model-00007-of-00014.safetensors",
185
+ "gpt_neox.layers.17.attention.masked_bias": "model-00006-of-00014.safetensors",
186
+ "gpt_neox.layers.17.attention.query_key_value.SCB": "model-00007-of-00014.safetensors",
187
+ "gpt_neox.layers.17.attention.query_key_value.bias": "model-00007-of-00014.safetensors",
188
+ "gpt_neox.layers.17.attention.query_key_value.weight": "model-00007-of-00014.safetensors",
189
+ "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
190
+ "gpt_neox.layers.17.input_layernorm.bias": "model-00006-of-00014.safetensors",
191
+ "gpt_neox.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors",
192
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.SCB": "model-00007-of-00014.safetensors",
193
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
194
+ "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
195
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.SCB": "model-00007-of-00014.safetensors",
196
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
197
+ "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
198
+ "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
199
+ "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
200
+ "gpt_neox.layers.18.attention.bias": "model-00007-of-00014.safetensors",
201
+ "gpt_neox.layers.18.attention.dense.SCB": "model-00007-of-00014.safetensors",
202
+ "gpt_neox.layers.18.attention.dense.bias": "model-00007-of-00014.safetensors",
203
+ "gpt_neox.layers.18.attention.dense.weight": "model-00007-of-00014.safetensors",
204
+ "gpt_neox.layers.18.attention.masked_bias": "model-00007-of-00014.safetensors",
205
+ "gpt_neox.layers.18.attention.query_key_value.SCB": "model-00007-of-00014.safetensors",
206
+ "gpt_neox.layers.18.attention.query_key_value.bias": "model-00007-of-00014.safetensors",
207
+ "gpt_neox.layers.18.attention.query_key_value.weight": "model-00007-of-00014.safetensors",
208
+ "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
209
+ "gpt_neox.layers.18.input_layernorm.bias": "model-00007-of-00014.safetensors",
210
+ "gpt_neox.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
211
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.SCB": "model-00007-of-00014.safetensors",
212
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
213
+ "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
214
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.SCB": "model-00007-of-00014.safetensors",
215
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
216
+ "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
217
+ "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
218
+ "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
219
+ "gpt_neox.layers.19.attention.bias": "model-00007-of-00014.safetensors",
220
+ "gpt_neox.layers.19.attention.dense.SCB": "model-00007-of-00014.safetensors",
221
+ "gpt_neox.layers.19.attention.dense.bias": "model-00007-of-00014.safetensors",
222
+ "gpt_neox.layers.19.attention.dense.weight": "model-00007-of-00014.safetensors",
223
+ "gpt_neox.layers.19.attention.masked_bias": "model-00007-of-00014.safetensors",
224
+ "gpt_neox.layers.19.attention.query_key_value.SCB": "model-00007-of-00014.safetensors",
225
+ "gpt_neox.layers.19.attention.query_key_value.bias": "model-00007-of-00014.safetensors",
226
+ "gpt_neox.layers.19.attention.query_key_value.weight": "model-00007-of-00014.safetensors",
227
+ "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
228
+ "gpt_neox.layers.19.input_layernorm.bias": "model-00007-of-00014.safetensors",
229
+ "gpt_neox.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
230
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.SCB": "model-00007-of-00014.safetensors",
231
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
232
+ "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
233
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.SCB": "model-00007-of-00014.safetensors",
234
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
235
+ "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
236
+ "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
237
+ "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
238
+ "gpt_neox.layers.2.attention.bias": "model-00001-of-00014.safetensors",
239
+ "gpt_neox.layers.2.attention.dense.SCB": "model-00002-of-00014.safetensors",
240
+ "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00014.safetensors",
241
+ "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00014.safetensors",
242
+ "gpt_neox.layers.2.attention.masked_bias": "model-00001-of-00014.safetensors",
243
+ "gpt_neox.layers.2.attention.query_key_value.SCB": "model-00002-of-00014.safetensors",
244
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00014.safetensors",
245
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00014.safetensors",
246
+ "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
247
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00014.safetensors",
248
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
249
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.SCB": "model-00002-of-00014.safetensors",
250
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
251
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
252
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.SCB": "model-00002-of-00014.safetensors",
253
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
254
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
255
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
256
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
257
+ "gpt_neox.layers.20.attention.bias": "model-00007-of-00014.safetensors",
258
+ "gpt_neox.layers.20.attention.dense.SCB": "model-00008-of-00014.safetensors",
259
+ "gpt_neox.layers.20.attention.dense.bias": "model-00008-of-00014.safetensors",
260
+ "gpt_neox.layers.20.attention.dense.weight": "model-00008-of-00014.safetensors",
261
+ "gpt_neox.layers.20.attention.masked_bias": "model-00007-of-00014.safetensors",
262
+ "gpt_neox.layers.20.attention.query_key_value.SCB": "model-00008-of-00014.safetensors",
263
+ "gpt_neox.layers.20.attention.query_key_value.bias": "model-00008-of-00014.safetensors",
264
+ "gpt_neox.layers.20.attention.query_key_value.weight": "model-00008-of-00014.safetensors",
265
+ "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
266
+ "gpt_neox.layers.20.input_layernorm.bias": "model-00007-of-00014.safetensors",
267
+ "gpt_neox.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors",
268
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.SCB": "model-00008-of-00014.safetensors",
269
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
270
+ "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
271
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.SCB": "model-00008-of-00014.safetensors",
272
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
273
+ "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
274
+ "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
275
+ "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
276
+ "gpt_neox.layers.21.attention.bias": "model-00008-of-00014.safetensors",
277
+ "gpt_neox.layers.21.attention.dense.SCB": "model-00008-of-00014.safetensors",
278
+ "gpt_neox.layers.21.attention.dense.bias": "model-00008-of-00014.safetensors",
279
+ "gpt_neox.layers.21.attention.dense.weight": "model-00008-of-00014.safetensors",
280
+ "gpt_neox.layers.21.attention.masked_bias": "model-00008-of-00014.safetensors",
281
+ "gpt_neox.layers.21.attention.query_key_value.SCB": "model-00008-of-00014.safetensors",
282
+ "gpt_neox.layers.21.attention.query_key_value.bias": "model-00008-of-00014.safetensors",
283
+ "gpt_neox.layers.21.attention.query_key_value.weight": "model-00008-of-00014.safetensors",
284
+ "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
285
+ "gpt_neox.layers.21.input_layernorm.bias": "model-00008-of-00014.safetensors",
286
+ "gpt_neox.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
287
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.SCB": "model-00008-of-00014.safetensors",
288
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
289
+ "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
290
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.SCB": "model-00008-of-00014.safetensors",
291
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
292
+ "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
293
+ "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
294
+ "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
295
+ "gpt_neox.layers.22.attention.bias": "model-00008-of-00014.safetensors",
296
+ "gpt_neox.layers.22.attention.dense.SCB": "model-00008-of-00014.safetensors",
297
+ "gpt_neox.layers.22.attention.dense.bias": "model-00008-of-00014.safetensors",
298
+ "gpt_neox.layers.22.attention.dense.weight": "model-00008-of-00014.safetensors",
299
+ "gpt_neox.layers.22.attention.masked_bias": "model-00008-of-00014.safetensors",
300
+ "gpt_neox.layers.22.attention.query_key_value.SCB": "model-00008-of-00014.safetensors",
301
+ "gpt_neox.layers.22.attention.query_key_value.bias": "model-00008-of-00014.safetensors",
302
+ "gpt_neox.layers.22.attention.query_key_value.weight": "model-00008-of-00014.safetensors",
303
+ "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
304
+ "gpt_neox.layers.22.input_layernorm.bias": "model-00008-of-00014.safetensors",
305
+ "gpt_neox.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
306
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.SCB": "model-00008-of-00014.safetensors",
307
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
308
+ "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
309
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.SCB": "model-00008-of-00014.safetensors",
310
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
311
+ "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
312
+ "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
313
+ "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
314
+ "gpt_neox.layers.23.attention.bias": "model-00008-of-00014.safetensors",
315
+ "gpt_neox.layers.23.attention.dense.SCB": "model-00009-of-00014.safetensors",
316
+ "gpt_neox.layers.23.attention.dense.bias": "model-00009-of-00014.safetensors",
317
+ "gpt_neox.layers.23.attention.dense.weight": "model-00009-of-00014.safetensors",
318
+ "gpt_neox.layers.23.attention.masked_bias": "model-00008-of-00014.safetensors",
319
+ "gpt_neox.layers.23.attention.query_key_value.SCB": "model-00009-of-00014.safetensors",
320
+ "gpt_neox.layers.23.attention.query_key_value.bias": "model-00009-of-00014.safetensors",
321
+ "gpt_neox.layers.23.attention.query_key_value.weight": "model-00009-of-00014.safetensors",
322
+ "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
323
+ "gpt_neox.layers.23.input_layernorm.bias": "model-00008-of-00014.safetensors",
324
+ "gpt_neox.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors",
325
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.SCB": "model-00009-of-00014.safetensors",
326
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
327
+ "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
328
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.SCB": "model-00009-of-00014.safetensors",
329
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
330
+ "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
331
+ "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
332
+ "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "gpt_neox.layers.24.attention.bias": "model-00009-of-00014.safetensors",
334
+ "gpt_neox.layers.24.attention.dense.SCB": "model-00009-of-00014.safetensors",
335
+ "gpt_neox.layers.24.attention.dense.bias": "model-00009-of-00014.safetensors",
336
+ "gpt_neox.layers.24.attention.dense.weight": "model-00009-of-00014.safetensors",
337
+ "gpt_neox.layers.24.attention.masked_bias": "model-00009-of-00014.safetensors",
338
+ "gpt_neox.layers.24.attention.query_key_value.SCB": "model-00009-of-00014.safetensors",
339
+ "gpt_neox.layers.24.attention.query_key_value.bias": "model-00009-of-00014.safetensors",
340
+ "gpt_neox.layers.24.attention.query_key_value.weight": "model-00009-of-00014.safetensors",
341
+ "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
342
+ "gpt_neox.layers.24.input_layernorm.bias": "model-00009-of-00014.safetensors",
343
+ "gpt_neox.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
344
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.SCB": "model-00009-of-00014.safetensors",
345
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
346
+ "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
347
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.SCB": "model-00009-of-00014.safetensors",
348
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
349
+ "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
350
+ "gpt_neox.layers.24.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
351
+ "gpt_neox.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
352
+ "gpt_neox.layers.25.attention.bias": "model-00009-of-00014.safetensors",
353
+ "gpt_neox.layers.25.attention.dense.SCB": "model-00009-of-00014.safetensors",
354
+ "gpt_neox.layers.25.attention.dense.bias": "model-00009-of-00014.safetensors",
355
+ "gpt_neox.layers.25.attention.dense.weight": "model-00009-of-00014.safetensors",
356
+ "gpt_neox.layers.25.attention.masked_bias": "model-00009-of-00014.safetensors",
357
+ "gpt_neox.layers.25.attention.query_key_value.SCB": "model-00009-of-00014.safetensors",
358
+ "gpt_neox.layers.25.attention.query_key_value.bias": "model-00009-of-00014.safetensors",
359
+ "gpt_neox.layers.25.attention.query_key_value.weight": "model-00009-of-00014.safetensors",
360
+ "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
361
+ "gpt_neox.layers.25.input_layernorm.bias": "model-00009-of-00014.safetensors",
362
+ "gpt_neox.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
363
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.SCB": "model-00009-of-00014.safetensors",
364
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
365
+ "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
366
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.SCB": "model-00009-of-00014.safetensors",
367
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
368
+ "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
369
+ "gpt_neox.layers.25.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
370
+ "gpt_neox.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
371
+ "gpt_neox.layers.26.attention.bias": "model-00009-of-00014.safetensors",
372
+ "gpt_neox.layers.26.attention.dense.SCB": "model-00010-of-00014.safetensors",
373
+ "gpt_neox.layers.26.attention.dense.bias": "model-00010-of-00014.safetensors",
374
+ "gpt_neox.layers.26.attention.dense.weight": "model-00010-of-00014.safetensors",
375
+ "gpt_neox.layers.26.attention.masked_bias": "model-00009-of-00014.safetensors",
376
+ "gpt_neox.layers.26.attention.query_key_value.SCB": "model-00010-of-00014.safetensors",
377
+ "gpt_neox.layers.26.attention.query_key_value.bias": "model-00010-of-00014.safetensors",
378
+ "gpt_neox.layers.26.attention.query_key_value.weight": "model-00010-of-00014.safetensors",
379
+ "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
380
+ "gpt_neox.layers.26.input_layernorm.bias": "model-00009-of-00014.safetensors",
381
+ "gpt_neox.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors",
382
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.SCB": "model-00010-of-00014.safetensors",
383
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
384
+ "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
385
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.SCB": "model-00010-of-00014.safetensors",
386
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
387
+ "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
388
+ "gpt_neox.layers.26.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
389
+ "gpt_neox.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
390
+ "gpt_neox.layers.27.attention.bias": "model-00010-of-00014.safetensors",
391
+ "gpt_neox.layers.27.attention.dense.SCB": "model-00010-of-00014.safetensors",
392
+ "gpt_neox.layers.27.attention.dense.bias": "model-00010-of-00014.safetensors",
393
+ "gpt_neox.layers.27.attention.dense.weight": "model-00010-of-00014.safetensors",
394
+ "gpt_neox.layers.27.attention.masked_bias": "model-00010-of-00014.safetensors",
395
+ "gpt_neox.layers.27.attention.query_key_value.SCB": "model-00010-of-00014.safetensors",
396
+ "gpt_neox.layers.27.attention.query_key_value.bias": "model-00010-of-00014.safetensors",
397
+ "gpt_neox.layers.27.attention.query_key_value.weight": "model-00010-of-00014.safetensors",
398
+ "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
399
+ "gpt_neox.layers.27.input_layernorm.bias": "model-00010-of-00014.safetensors",
400
+ "gpt_neox.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
401
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.SCB": "model-00010-of-00014.safetensors",
402
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
403
+ "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
404
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.SCB": "model-00010-of-00014.safetensors",
405
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
406
+ "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
407
+ "gpt_neox.layers.27.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
408
+ "gpt_neox.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
409
+ "gpt_neox.layers.28.attention.bias": "model-00010-of-00014.safetensors",
410
+ "gpt_neox.layers.28.attention.dense.SCB": "model-00010-of-00014.safetensors",
411
+ "gpt_neox.layers.28.attention.dense.bias": "model-00010-of-00014.safetensors",
412
+ "gpt_neox.layers.28.attention.dense.weight": "model-00010-of-00014.safetensors",
413
+ "gpt_neox.layers.28.attention.masked_bias": "model-00010-of-00014.safetensors",
414
+ "gpt_neox.layers.28.attention.query_key_value.SCB": "model-00010-of-00014.safetensors",
415
+ "gpt_neox.layers.28.attention.query_key_value.bias": "model-00010-of-00014.safetensors",
416
+ "gpt_neox.layers.28.attention.query_key_value.weight": "model-00010-of-00014.safetensors",
417
+ "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
418
+ "gpt_neox.layers.28.input_layernorm.bias": "model-00010-of-00014.safetensors",
419
+ "gpt_neox.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
420
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.SCB": "model-00010-of-00014.safetensors",
421
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
422
+ "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
423
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.SCB": "model-00010-of-00014.safetensors",
424
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
425
+ "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
426
+ "gpt_neox.layers.28.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
427
+ "gpt_neox.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
428
+ "gpt_neox.layers.29.attention.bias": "model-00010-of-00014.safetensors",
429
+ "gpt_neox.layers.29.attention.dense.SCB": "model-00011-of-00014.safetensors",
430
+ "gpt_neox.layers.29.attention.dense.bias": "model-00011-of-00014.safetensors",
431
+ "gpt_neox.layers.29.attention.dense.weight": "model-00011-of-00014.safetensors",
432
+ "gpt_neox.layers.29.attention.masked_bias": "model-00010-of-00014.safetensors",
433
+ "gpt_neox.layers.29.attention.query_key_value.SCB": "model-00011-of-00014.safetensors",
434
+ "gpt_neox.layers.29.attention.query_key_value.bias": "model-00011-of-00014.safetensors",
435
+ "gpt_neox.layers.29.attention.query_key_value.weight": "model-00011-of-00014.safetensors",
436
+ "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
437
+ "gpt_neox.layers.29.input_layernorm.bias": "model-00010-of-00014.safetensors",
438
+ "gpt_neox.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors",
439
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.SCB": "model-00011-of-00014.safetensors",
440
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
441
+ "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
442
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.SCB": "model-00011-of-00014.safetensors",
443
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
444
+ "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
445
+ "gpt_neox.layers.29.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
446
+ "gpt_neox.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
447
+ "gpt_neox.layers.3.attention.bias": "model-00002-of-00014.safetensors",
448
+ "gpt_neox.layers.3.attention.dense.SCB": "model-00002-of-00014.safetensors",
449
+ "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00014.safetensors",
450
+ "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00014.safetensors",
451
+ "gpt_neox.layers.3.attention.masked_bias": "model-00002-of-00014.safetensors",
452
+ "gpt_neox.layers.3.attention.query_key_value.SCB": "model-00002-of-00014.safetensors",
453
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00014.safetensors",
454
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00014.safetensors",
455
+ "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
456
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00014.safetensors",
457
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
458
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.SCB": "model-00002-of-00014.safetensors",
459
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
460
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
461
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.SCB": "model-00002-of-00014.safetensors",
462
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
463
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
464
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
465
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
466
+ "gpt_neox.layers.30.attention.bias": "model-00011-of-00014.safetensors",
467
+ "gpt_neox.layers.30.attention.dense.SCB": "model-00011-of-00014.safetensors",
468
+ "gpt_neox.layers.30.attention.dense.bias": "model-00011-of-00014.safetensors",
469
+ "gpt_neox.layers.30.attention.dense.weight": "model-00011-of-00014.safetensors",
470
+ "gpt_neox.layers.30.attention.masked_bias": "model-00011-of-00014.safetensors",
471
+ "gpt_neox.layers.30.attention.query_key_value.SCB": "model-00011-of-00014.safetensors",
472
+ "gpt_neox.layers.30.attention.query_key_value.bias": "model-00011-of-00014.safetensors",
473
+ "gpt_neox.layers.30.attention.query_key_value.weight": "model-00011-of-00014.safetensors",
474
+ "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
475
+ "gpt_neox.layers.30.input_layernorm.bias": "model-00011-of-00014.safetensors",
476
+ "gpt_neox.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
477
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.SCB": "model-00011-of-00014.safetensors",
478
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
479
+ "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
480
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.SCB": "model-00011-of-00014.safetensors",
481
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
482
+ "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
483
+ "gpt_neox.layers.30.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
484
+ "gpt_neox.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
485
+ "gpt_neox.layers.31.attention.bias": "model-00011-of-00014.safetensors",
486
+ "gpt_neox.layers.31.attention.dense.SCB": "model-00011-of-00014.safetensors",
487
+ "gpt_neox.layers.31.attention.dense.bias": "model-00011-of-00014.safetensors",
488
+ "gpt_neox.layers.31.attention.dense.weight": "model-00011-of-00014.safetensors",
489
+ "gpt_neox.layers.31.attention.masked_bias": "model-00011-of-00014.safetensors",
490
+ "gpt_neox.layers.31.attention.query_key_value.SCB": "model-00011-of-00014.safetensors",
491
+ "gpt_neox.layers.31.attention.query_key_value.bias": "model-00011-of-00014.safetensors",
492
+ "gpt_neox.layers.31.attention.query_key_value.weight": "model-00011-of-00014.safetensors",
493
+ "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
494
+ "gpt_neox.layers.31.input_layernorm.bias": "model-00011-of-00014.safetensors",
495
+ "gpt_neox.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
496
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.SCB": "model-00011-of-00014.safetensors",
497
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
498
+ "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
499
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.SCB": "model-00011-of-00014.safetensors",
500
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
501
+ "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
502
+ "gpt_neox.layers.31.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
503
+ "gpt_neox.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
504
+ "gpt_neox.layers.32.attention.bias": "model-00011-of-00014.safetensors",
505
+ "gpt_neox.layers.32.attention.dense.SCB": "model-00012-of-00014.safetensors",
506
+ "gpt_neox.layers.32.attention.dense.bias": "model-00012-of-00014.safetensors",
507
+ "gpt_neox.layers.32.attention.dense.weight": "model-00012-of-00014.safetensors",
508
+ "gpt_neox.layers.32.attention.masked_bias": "model-00011-of-00014.safetensors",
509
+ "gpt_neox.layers.32.attention.query_key_value.SCB": "model-00012-of-00014.safetensors",
510
+ "gpt_neox.layers.32.attention.query_key_value.bias": "model-00012-of-00014.safetensors",
511
+ "gpt_neox.layers.32.attention.query_key_value.weight": "model-00012-of-00014.safetensors",
512
+ "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
513
+ "gpt_neox.layers.32.input_layernorm.bias": "model-00011-of-00014.safetensors",
514
+ "gpt_neox.layers.32.input_layernorm.weight": "model-00011-of-00014.safetensors",
515
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.SCB": "model-00012-of-00014.safetensors",
516
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
517
+ "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
518
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.SCB": "model-00012-of-00014.safetensors",
519
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
520
+ "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
521
+ "gpt_neox.layers.32.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
522
+ "gpt_neox.layers.32.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
523
+ "gpt_neox.layers.33.attention.bias": "model-00012-of-00014.safetensors",
524
+ "gpt_neox.layers.33.attention.dense.SCB": "model-00012-of-00014.safetensors",
525
+ "gpt_neox.layers.33.attention.dense.bias": "model-00012-of-00014.safetensors",
526
+ "gpt_neox.layers.33.attention.dense.weight": "model-00012-of-00014.safetensors",
527
+ "gpt_neox.layers.33.attention.masked_bias": "model-00012-of-00014.safetensors",
528
+ "gpt_neox.layers.33.attention.query_key_value.SCB": "model-00012-of-00014.safetensors",
529
+ "gpt_neox.layers.33.attention.query_key_value.bias": "model-00012-of-00014.safetensors",
530
+ "gpt_neox.layers.33.attention.query_key_value.weight": "model-00012-of-00014.safetensors",
531
+ "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
532
+ "gpt_neox.layers.33.input_layernorm.bias": "model-00012-of-00014.safetensors",
533
+ "gpt_neox.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
534
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.SCB": "model-00012-of-00014.safetensors",
535
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
536
+ "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
537
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.SCB": "model-00012-of-00014.safetensors",
538
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
539
+ "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
540
+ "gpt_neox.layers.33.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
541
+ "gpt_neox.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
542
+ "gpt_neox.layers.34.attention.bias": "model-00012-of-00014.safetensors",
543
+ "gpt_neox.layers.34.attention.dense.SCB": "model-00012-of-00014.safetensors",
544
+ "gpt_neox.layers.34.attention.dense.bias": "model-00012-of-00014.safetensors",
545
+ "gpt_neox.layers.34.attention.dense.weight": "model-00012-of-00014.safetensors",
546
+ "gpt_neox.layers.34.attention.masked_bias": "model-00012-of-00014.safetensors",
547
+ "gpt_neox.layers.34.attention.query_key_value.SCB": "model-00012-of-00014.safetensors",
548
+ "gpt_neox.layers.34.attention.query_key_value.bias": "model-00012-of-00014.safetensors",
549
+ "gpt_neox.layers.34.attention.query_key_value.weight": "model-00012-of-00014.safetensors",
550
+ "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
551
+ "gpt_neox.layers.34.input_layernorm.bias": "model-00012-of-00014.safetensors",
552
+ "gpt_neox.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
553
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.SCB": "model-00012-of-00014.safetensors",
554
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
555
+ "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
556
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.SCB": "model-00012-of-00014.safetensors",
557
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
558
+ "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
559
+ "gpt_neox.layers.34.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
560
+ "gpt_neox.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
561
+ "gpt_neox.layers.35.attention.bias": "model-00012-of-00014.safetensors",
562
+ "gpt_neox.layers.35.attention.dense.SCB": "model-00013-of-00014.safetensors",
563
+ "gpt_neox.layers.35.attention.dense.bias": "model-00013-of-00014.safetensors",
564
+ "gpt_neox.layers.35.attention.dense.weight": "model-00013-of-00014.safetensors",
565
+ "gpt_neox.layers.35.attention.masked_bias": "model-00012-of-00014.safetensors",
566
+ "gpt_neox.layers.35.attention.query_key_value.SCB": "model-00013-of-00014.safetensors",
567
+ "gpt_neox.layers.35.attention.query_key_value.bias": "model-00013-of-00014.safetensors",
568
+ "gpt_neox.layers.35.attention.query_key_value.weight": "model-00013-of-00014.safetensors",
569
+ "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
570
+ "gpt_neox.layers.35.input_layernorm.bias": "model-00012-of-00014.safetensors",
571
+ "gpt_neox.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors",
572
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.SCB": "model-00013-of-00014.safetensors",
573
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
574
+ "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
575
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.SCB": "model-00013-of-00014.safetensors",
576
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
577
+ "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
578
+ "gpt_neox.layers.35.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
579
+ "gpt_neox.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
580
+ "gpt_neox.layers.36.attention.bias": "model-00013-of-00014.safetensors",
581
+ "gpt_neox.layers.36.attention.dense.SCB": "model-00013-of-00014.safetensors",
582
+ "gpt_neox.layers.36.attention.dense.bias": "model-00013-of-00014.safetensors",
583
+ "gpt_neox.layers.36.attention.dense.weight": "model-00013-of-00014.safetensors",
584
+ "gpt_neox.layers.36.attention.masked_bias": "model-00013-of-00014.safetensors",
585
+ "gpt_neox.layers.36.attention.query_key_value.SCB": "model-00013-of-00014.safetensors",
586
+ "gpt_neox.layers.36.attention.query_key_value.bias": "model-00013-of-00014.safetensors",
587
+ "gpt_neox.layers.36.attention.query_key_value.weight": "model-00013-of-00014.safetensors",
588
+ "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
589
+ "gpt_neox.layers.36.input_layernorm.bias": "model-00013-of-00014.safetensors",
590
+ "gpt_neox.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
591
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.SCB": "model-00013-of-00014.safetensors",
592
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
593
+ "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
594
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.SCB": "model-00013-of-00014.safetensors",
595
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
596
+ "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
597
+ "gpt_neox.layers.36.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
598
+ "gpt_neox.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
599
+ "gpt_neox.layers.37.attention.bias": "model-00013-of-00014.safetensors",
600
+ "gpt_neox.layers.37.attention.dense.SCB": "model-00013-of-00014.safetensors",
601
+ "gpt_neox.layers.37.attention.dense.bias": "model-00013-of-00014.safetensors",
602
+ "gpt_neox.layers.37.attention.dense.weight": "model-00013-of-00014.safetensors",
603
+ "gpt_neox.layers.37.attention.masked_bias": "model-00013-of-00014.safetensors",
604
+ "gpt_neox.layers.37.attention.query_key_value.SCB": "model-00013-of-00014.safetensors",
605
+ "gpt_neox.layers.37.attention.query_key_value.bias": "model-00013-of-00014.safetensors",
606
+ "gpt_neox.layers.37.attention.query_key_value.weight": "model-00013-of-00014.safetensors",
607
+ "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
608
+ "gpt_neox.layers.37.input_layernorm.bias": "model-00013-of-00014.safetensors",
609
+ "gpt_neox.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
610
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.SCB": "model-00013-of-00014.safetensors",
611
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
612
+ "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
613
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.SCB": "model-00013-of-00014.safetensors",
614
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
615
+ "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
616
+ "gpt_neox.layers.37.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
617
+ "gpt_neox.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
618
+ "gpt_neox.layers.38.attention.bias": "model-00013-of-00014.safetensors",
619
+ "gpt_neox.layers.38.attention.dense.SCB": "model-00014-of-00014.safetensors",
620
+ "gpt_neox.layers.38.attention.dense.bias": "model-00014-of-00014.safetensors",
621
+ "gpt_neox.layers.38.attention.dense.weight": "model-00014-of-00014.safetensors",
622
+ "gpt_neox.layers.38.attention.masked_bias": "model-00013-of-00014.safetensors",
623
+ "gpt_neox.layers.38.attention.query_key_value.SCB": "model-00014-of-00014.safetensors",
624
+ "gpt_neox.layers.38.attention.query_key_value.bias": "model-00014-of-00014.safetensors",
625
+ "gpt_neox.layers.38.attention.query_key_value.weight": "model-00014-of-00014.safetensors",
626
+ "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
627
+ "gpt_neox.layers.38.input_layernorm.bias": "model-00013-of-00014.safetensors",
628
+ "gpt_neox.layers.38.input_layernorm.weight": "model-00013-of-00014.safetensors",
629
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.SCB": "model-00014-of-00014.safetensors",
630
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
631
+ "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
632
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.SCB": "model-00014-of-00014.safetensors",
633
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
634
+ "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
635
+ "gpt_neox.layers.38.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
636
+ "gpt_neox.layers.38.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
637
+ "gpt_neox.layers.39.attention.bias": "model-00014-of-00014.safetensors",
638
+ "gpt_neox.layers.39.attention.dense.SCB": "model-00014-of-00014.safetensors",
639
+ "gpt_neox.layers.39.attention.dense.bias": "model-00014-of-00014.safetensors",
640
+ "gpt_neox.layers.39.attention.dense.weight": "model-00014-of-00014.safetensors",
641
+ "gpt_neox.layers.39.attention.masked_bias": "model-00014-of-00014.safetensors",
642
+ "gpt_neox.layers.39.attention.query_key_value.SCB": "model-00014-of-00014.safetensors",
643
+ "gpt_neox.layers.39.attention.query_key_value.bias": "model-00014-of-00014.safetensors",
644
+ "gpt_neox.layers.39.attention.query_key_value.weight": "model-00014-of-00014.safetensors",
645
+ "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "model-00014-of-00014.safetensors",
646
+ "gpt_neox.layers.39.input_layernorm.bias": "model-00014-of-00014.safetensors",
647
+ "gpt_neox.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
648
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.SCB": "model-00014-of-00014.safetensors",
649
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
650
+ "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
651
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.SCB": "model-00014-of-00014.safetensors",
652
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
653
+ "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
654
+ "gpt_neox.layers.39.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
655
+ "gpt_neox.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
656
+ "gpt_neox.layers.4.attention.bias": "model-00002-of-00014.safetensors",
657
+ "gpt_neox.layers.4.attention.dense.SCB": "model-00002-of-00014.safetensors",
658
+ "gpt_neox.layers.4.attention.dense.bias": "model-00002-of-00014.safetensors",
659
+ "gpt_neox.layers.4.attention.dense.weight": "model-00002-of-00014.safetensors",
660
+ "gpt_neox.layers.4.attention.masked_bias": "model-00002-of-00014.safetensors",
661
+ "gpt_neox.layers.4.attention.query_key_value.SCB": "model-00002-of-00014.safetensors",
662
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00002-of-00014.safetensors",
663
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00002-of-00014.safetensors",
664
+ "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
665
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00002-of-00014.safetensors",
666
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
667
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.SCB": "model-00002-of-00014.safetensors",
668
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
669
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
670
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.SCB": "model-00002-of-00014.safetensors",
671
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
672
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
673
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
674
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
675
+ "gpt_neox.layers.5.attention.bias": "model-00002-of-00014.safetensors",
676
+ "gpt_neox.layers.5.attention.dense.SCB": "model-00003-of-00014.safetensors",
677
+ "gpt_neox.layers.5.attention.dense.bias": "model-00003-of-00014.safetensors",
678
+ "gpt_neox.layers.5.attention.dense.weight": "model-00003-of-00014.safetensors",
679
+ "gpt_neox.layers.5.attention.masked_bias": "model-00002-of-00014.safetensors",
680
+ "gpt_neox.layers.5.attention.query_key_value.SCB": "model-00003-of-00014.safetensors",
681
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00003-of-00014.safetensors",
682
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00003-of-00014.safetensors",
683
+ "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
684
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00002-of-00014.safetensors",
685
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
686
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.SCB": "model-00003-of-00014.safetensors",
687
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
688
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
689
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.SCB": "model-00003-of-00014.safetensors",
690
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
691
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
692
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
693
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
694
+ "gpt_neox.layers.6.attention.bias": "model-00003-of-00014.safetensors",
695
+ "gpt_neox.layers.6.attention.dense.SCB": "model-00003-of-00014.safetensors",
696
+ "gpt_neox.layers.6.attention.dense.bias": "model-00003-of-00014.safetensors",
697
+ "gpt_neox.layers.6.attention.dense.weight": "model-00003-of-00014.safetensors",
698
+ "gpt_neox.layers.6.attention.masked_bias": "model-00003-of-00014.safetensors",
699
+ "gpt_neox.layers.6.attention.query_key_value.SCB": "model-00003-of-00014.safetensors",
700
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00003-of-00014.safetensors",
701
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00003-of-00014.safetensors",
702
+ "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
703
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00003-of-00014.safetensors",
704
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
705
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.SCB": "model-00003-of-00014.safetensors",
706
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
707
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
708
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.SCB": "model-00003-of-00014.safetensors",
709
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
710
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
711
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
712
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
713
+ "gpt_neox.layers.7.attention.bias": "model-00003-of-00014.safetensors",
714
+ "gpt_neox.layers.7.attention.dense.SCB": "model-00003-of-00014.safetensors",
715
+ "gpt_neox.layers.7.attention.dense.bias": "model-00003-of-00014.safetensors",
716
+ "gpt_neox.layers.7.attention.dense.weight": "model-00003-of-00014.safetensors",
717
+ "gpt_neox.layers.7.attention.masked_bias": "model-00003-of-00014.safetensors",
718
+ "gpt_neox.layers.7.attention.query_key_value.SCB": "model-00003-of-00014.safetensors",
719
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00003-of-00014.safetensors",
720
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00003-of-00014.safetensors",
721
+ "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
722
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00003-of-00014.safetensors",
723
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
724
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.SCB": "model-00003-of-00014.safetensors",
725
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
726
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
727
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.SCB": "model-00003-of-00014.safetensors",
728
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
729
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
730
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
731
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
732
+ "gpt_neox.layers.8.attention.bias": "model-00003-of-00014.safetensors",
733
+ "gpt_neox.layers.8.attention.dense.SCB": "model-00004-of-00014.safetensors",
734
+ "gpt_neox.layers.8.attention.dense.bias": "model-00004-of-00014.safetensors",
735
+ "gpt_neox.layers.8.attention.dense.weight": "model-00004-of-00014.safetensors",
736
+ "gpt_neox.layers.8.attention.masked_bias": "model-00003-of-00014.safetensors",
737
+ "gpt_neox.layers.8.attention.query_key_value.SCB": "model-00004-of-00014.safetensors",
738
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00004-of-00014.safetensors",
739
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00004-of-00014.safetensors",
740
+ "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
741
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00003-of-00014.safetensors",
742
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
743
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.SCB": "model-00004-of-00014.safetensors",
744
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
745
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
746
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.SCB": "model-00004-of-00014.safetensors",
747
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
748
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
749
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
750
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
751
+ "gpt_neox.layers.9.attention.bias": "model-00004-of-00014.safetensors",
752
+ "gpt_neox.layers.9.attention.dense.SCB": "model-00004-of-00014.safetensors",
753
+ "gpt_neox.layers.9.attention.dense.bias": "model-00004-of-00014.safetensors",
754
+ "gpt_neox.layers.9.attention.dense.weight": "model-00004-of-00014.safetensors",
755
+ "gpt_neox.layers.9.attention.masked_bias": "model-00004-of-00014.safetensors",
756
+ "gpt_neox.layers.9.attention.query_key_value.SCB": "model-00004-of-00014.safetensors",
757
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00004-of-00014.safetensors",
758
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00004-of-00014.safetensors",
759
+ "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
760
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00004-of-00014.safetensors",
761
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
762
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.SCB": "model-00004-of-00014.safetensors",
763
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
764
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
765
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.SCB": "model-00004-of-00014.safetensors",
766
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
767
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
768
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
769
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors"
770
+ }
771
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "eos_token": "<|endoftext|>",
10
+ "pad_token": "<|endoftext|>"
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<|endoftext|>",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "<|endoftext|>",
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }