Hugging Face's logo

arthrod
/
clau_creat

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Model card Files
xet
Community
arthrod commited on
Commit
b21c64e
·
verified ·
1 Parent(s): 79f716a

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .ipynb_checkpoints/Untitled-checkpoint.ipynb +6 -0
  2. Untitled.ipynb +734 -0
  3. step_final/added_tokens.json +8 -0
  4. step_final/config.json +26 -0
  5. step_final/generation_config.json +6 -0
  6. step_final/pytorch_model-00001-of-00002.bin +3 -0
  7. step_final/pytorch_model-00002-of-00002.bin +3 -0
  8. step_final/pytorch_model.bin.index.json +298 -0
  9. step_final/special_tokens_map.json +13 -0
  10. step_final/tokenizer.model +3 -0
  11. step_final/tokenizer_config.json +77 -0
.ipynb_checkpoints/Untitled-checkpoint.ipynb ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [],
3
+ "metadata": {},
4
+ "nbformat": 4,
5
+ "nbformat_minor": 5
6
+ }
Untitled.ipynb ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "id": "64361b9e-39fe-4777-9887-68712aa1098b",
7
+ "metadata": {},
8
+ "outputs": [],
9
+ "source": [
10
+ "#Model Commit"
11
+ ]
12
+ },
13
+ {
14
+ "cell_type": "code",
15
+ "execution_count": 3,
16
+ "id": "9483d5c4-b8c5-48f8-b86d-bde850edc532",
17
+ "metadata": {},
18
+ "outputs": [
19
+ {
20
+ "name": "stdout",
21
+ "output_type": "stream",
22
+ "text": [
23
+ "Requirement already satisfied: huggingface_hub in /opt/conda/lib/python3.10/site-packages (0.21.3)\n",
24
+ "Collecting python-dotenv\n",
25
+ " Downloading python_dotenv-1.0.1-py3-none-any.whl.metadata (23 kB)\n",
26
+ "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (3.13.1)\n",
27
+ "Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2023.12.2)\n",
28
+ "Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2.31.0)\n",
29
+ "Requirement already satisfied: tqdm>=4.42.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.65.0)\n",
30
+ "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (6.0.1)\n",
31
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.9.0)\n",
32
+ "Requirement already satisfied: packaging>=20.9 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (23.1)\n",
33
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2.0.4)\n",
34
+ "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (3.4)\n",
35
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (1.26.18)\n",
36
+ "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2023.11.17)\n",
37
+ "Downloading python_dotenv-1.0.1-py3-none-any.whl (19 kB)\n",
38
+ "Installing collected packages: python-dotenv\n",
39
+ "Successfully installed python-dotenv-1.0.1\n",
40
+ "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
41
+ "\u001b[0m"
42
+ ]
43
+ }
44
+ ],
45
+ "source": [
46
+ "!pip install huggingface_hub python-dotenv"
47
+ ]
48
+ },
49
+ {
50
+ "cell_type": "code",
51
+ "execution_count": 4,
52
+ "id": "93c881e9-1081-4ab8-883e-c0bd8abb241e",
53
+ "metadata": {},
54
+ "outputs": [
55
+ {
56
+ "name": "stdout",
57
+ "output_type": "stream",
58
+ "text": [
59
+ "Token has not been saved to git credential helper. Pass `add_to_git_credential=True` if you want to set the git credential as well.\n",
60
+ "Token is valid (permission: write).\n",
61
+ "Your token has been saved to /root/.cache/huggingface/token\n",
62
+ "Login successful\n"
63
+ ]
64
+ }
65
+ ],
66
+ "source": [
67
+ "from dotenv import load_dotenv\n",
68
+ "import os\n",
69
+ "from huggingface_hub import login, hf_hub_download\n",
70
+ "\n",
71
+ "# Load environment variables from .env file\n",
72
+ "load_dotenv()\n",
73
+ "\n",
74
+ "# Retrieve the Hugging Face token from the environment variable\n",
75
+ "hf_token = os.getenv(\"HF_TOKEN\")\n",
76
+ "\n",
77
+ "# Ensure the token is present\n",
78
+ "if not hf_token:\n",
79
+ " raise ValueError(\"Hugging Face token not found. Make sure your .env file is configured correctly and HF_TOKEN is set.\")\n",
80
+ "\n",
81
+ "# Authenticate with Hugging Face using the token\n",
82
+ "login(token=hf_token)"
83
+ ]
84
+ },
85
+ {
86
+ "cell_type": "code",
87
+ "execution_count": 7,
88
+ "id": "6c7c4ca0-31fe-4dd5-ae42-136ddf947983",
89
+ "metadata": {},
90
+ "outputs": [
91
+ {
92
+ "name": "stdout",
93
+ "output_type": "stream",
94
+ "text": [
95
+ "Collecting package metadata (current_repodata.json): done\n",
96
+ "Solving environment: done\n",
97
+ "\n",
98
+ "\n",
99
+ "==> WARNING: A newer version of conda exists. <==\n",
100
+ " current version: 23.9.0\n",
101
+ " latest version: 24.1.2\n",
102
+ "\n",
103
+ "Please update conda by running\n",
104
+ "\n",
105
+ " $ conda update -n base -c defaults conda\n",
106
+ "\n",
107
+ "Or to minimize the number of packages updated during conda update use\n",
108
+ "\n",
109
+ " conda install conda=24.1.2\n",
110
+ "\n",
111
+ "\n",
112
+ "\n",
113
+ "## Package Plan ##\n",
114
+ "\n",
115
+ " environment location: /opt/conda\n",
116
+ "\n",
117
+ " added / updated specs:\n",
118
+ " - git\n",
119
+ "\n",
120
+ "\n",
121
+ "The following packages will be downloaded:\n",
122
+ "\n",
123
+ " package | build\n",
124
+ " ---------------------------|-----------------\n",
125
+ " ca-certificates-2023.08.22 | h06a4308_0 130 KB anaconda\n",
126
+ " certifi-2023.11.17 | py310h06a4308_0 159 KB anaconda\n",
127
+ " curl-8.4.0 | hdbd6064_0 90 KB anaconda\n",
128
+ " gdbm-1.18 | hd4cb3f1_4 193 KB anaconda\n",
129
+ " gettext-0.21.0 | h39681ba_1 3.4 MB anaconda\n",
130
+ " git-2.40.1 | pl5340h36fbf9e_1 9.9 MB\n",
131
+ " libcurl-8.4.0 | h251f7ec_0 388 KB anaconda\n",
132
+ " openssl-3.0.12 | h7f8727e_0 5.2 MB anaconda\n",
133
+ " perl-5.34.0 | h5eee18b_2 13.3 MB anaconda\n",
134
+ " ------------------------------------------------------------\n",
135
+ " Total: 32.8 MB\n",
136
+ "\n",
137
+ "The following NEW packages will be INSTALLED:\n",
138
+ "\n",
139
+ " curl anaconda/linux-64::curl-8.4.0-hdbd6064_0 \n",
140
+ " gdbm anaconda/linux-64::gdbm-1.18-hd4cb3f1_4 \n",
141
+ " gettext anaconda/linux-64::gettext-0.21.0-h39681ba_1 \n",
142
+ " git pkgs/main/linux-64::git-2.40.1-pl5340h36fbf9e_1 \n",
143
+ " perl anaconda/linux-64::perl-5.34.0-h5eee18b_2 \n",
144
+ "\n",
145
+ "The following packages will be SUPERSEDED by a higher-priority channel:\n",
146
+ "\n",
147
+ " ca-certificates pkgs/main::ca-certificates-2023.12.12~ --> anaconda::ca-certificates-2023.08.22-h06a4308_0 \n",
148
+ " certifi pkgs/main --> anaconda \n",
149
+ " libcurl pkgs/main::libcurl-8.4.0-h251f7ec_1 --> anaconda::libcurl-8.4.0-h251f7ec_0 \n",
150
+ " openssl pkgs/main --> anaconda \n",
151
+ "\n",
152
+ "\n",
153
+ "\n",
154
+ "Downloading and Extracting Packages:\n",
155
+ "libcurl-8.4.0 | 388 KB | | 0% \n",
156
+ "perl-5.34.0 | 13.3 MB | | 0% \u001b[A\n",
157
+ "\n",
158
+ "git-2.40.1 | 9.9 MB | | 0% \u001b[A\u001b[A\n",
159
+ "\n",
160
+ "\n",
161
+ "certifi-2023.11.17 | 159 KB | | 0% \u001b[A\u001b[A\u001b[A\n",
162
+ "\n",
163
+ "\n",
164
+ "\n",
165
+ "openssl-3.0.12 | 5.2 MB | | 0% \u001b[A\u001b[A\u001b[A\u001b[A\n",
166
+ "\n",
167
+ "\n",
168
+ "\n",
169
+ "\n",
170
+ "curl-8.4.0 | 90 KB | | 0% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
171
+ "\n",
172
+ "\n",
173
+ "\n",
174
+ "\n",
175
+ "\n",
176
+ "ca-certificates-2023 | 130 KB | | 0% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
177
+ "\n",
178
+ "\n",
179
+ "\n",
180
+ "\n",
181
+ "\n",
182
+ "\n",
183
+ "gettext-0.21.0 | 3.4 MB | | 0% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
184
+ "\n",
185
+ "\n",
186
+ "\n",
187
+ "\n",
188
+ "\n",
189
+ "\n",
190
+ "\n",
191
+ "gdbm-1.18 | 193 KB | | 0% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
192
+ "\n",
193
+ "libcurl-8.4.0 | 388 KB | #5 | 4% \u001b[A\u001b[A\n",
194
+ "\n",
195
+ "\n",
196
+ "certifi-2023.11.17 | 159 KB | ###7 | 10% \u001b[A\u001b[A\u001b[A\n",
197
+ "\n",
198
+ "\n",
199
+ "\n",
200
+ "openssl-3.0.12 | 5.2 MB | 1 | 0% \u001b[A\u001b[A\u001b[A\u001b[A\n",
201
+ "perl-5.34.0 | 13.3 MB | | 0% \u001b[A\n",
202
+ "\n",
203
+ "git-2.40.1 | 9.9 MB | ##########6 | 29% \u001b[A\u001b[A\n",
204
+ "\n",
205
+ "\n",
206
+ "\n",
207
+ "\n",
208
+ "\n",
209
+ "ca-certificates-2023 | 130 KB | ####5 | 12% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
210
+ "\n",
211
+ "\n",
212
+ "\n",
213
+ "openssl-3.0.12 | 5.2 MB | #####7 | 16% \u001b[A\u001b[A\u001b[A\u001b[A\n",
214
+ "\n",
215
+ "\n",
216
+ "\n",
217
+ "\n",
218
+ "curl-8.4.0 | 90 KB | ######6 | 18% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
219
+ "perl-5.34.0 | 13.3 MB | #3 | 4% \u001b[A\n",
220
+ "\n",
221
+ "\n",
222
+ "\n",
223
+ "\n",
224
+ "\n",
225
+ "ca-certificates-2023 | 130 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
226
+ "\n",
227
+ "libcurl-8.4.0 | 388 KB | ##################################### | 100% \u001b[A\u001b[A\n",
228
+ "\n",
229
+ "\n",
230
+ "certifi-2023.11.17 | 159 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\n",
231
+ "\n",
232
+ "\n",
233
+ "certifi-2023.11.17 | 159 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\n",
234
+ "\n",
235
+ "\n",
236
+ "\n",
237
+ "\n",
238
+ "\n",
239
+ "\n",
240
+ "gettext-0.21.0 | 3.4 MB | 1 | 0% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
241
+ "\n",
242
+ "\n",
243
+ "\n",
244
+ "\n",
245
+ "curl-8.4.0 | 90 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
246
+ "\n",
247
+ "\n",
248
+ "\n",
249
+ "openssl-3.0.12 | 5.2 MB | #######################7 | 64% \u001b[A\u001b[A\u001b[A\u001b[A\n",
250
+ "\n",
251
+ "\n",
252
+ "\n",
253
+ "\n",
254
+ "\n",
255
+ "\n",
256
+ "\n",
257
+ "gdbm-1.18 | 193 KB | ### | 8% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
258
+ "perl-5.34.0 | 13.3 MB | ####6 | 12% \u001b[A\n",
259
+ "perl-5.34.0 | 13.3 MB | ########6 | 23% \u001b[A\n",
260
+ "perl-5.34.0 | 13.3 MB | ###############6 | 42% \u001b[A\n",
261
+ "\n",
262
+ "\n",
263
+ "\n",
264
+ "\n",
265
+ "\n",
266
+ "\n",
267
+ "\n",
268
+ "gdbm-1.18 | 193 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
269
+ "\n",
270
+ "\n",
271
+ "\n",
272
+ "\n",
273
+ "\n",
274
+ "\n",
275
+ "\n",
276
+ "gdbm-1.18 | 193 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
277
+ "perl-5.34.0 | 13.3 MB | ########################3 | 66% \u001b[A\n",
278
+ "perl-5.34.0 | 13.3 MB | ##############################8 | 83% \u001b[A\n",
279
+ "\n",
280
+ "git-2.40.1 | 9.9 MB | ##################################### | 100% \u001b[A\u001b[A\n",
281
+ "\n",
282
+ "git-2.40.1 | 9.9 MB | ##################################### | 100% \u001b[A\u001b[A\n",
283
+ "\n",
284
+ "\n",
285
+ "\n",
286
+ "\n",
287
+ "\n",
288
+ "\n",
289
+ "gettext-0.21.0 | 3.4 MB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
290
+ "\n",
291
+ "\n",
292
+ "\n",
293
+ "\n",
294
+ "\n",
295
+ "\n",
296
+ "gettext-0.21.0 | 3.4 MB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
297
+ "\n",
298
+ "\n",
299
+ "\n",
300
+ "openssl-3.0.12 | 5.2 MB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\n",
301
+ "\n",
302
+ "\n",
303
+ "\n",
304
+ "openssl-3.0.12 | 5.2 MB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\u001b[A\n",
305
+ "perl-5.34.0 | 13.3 MB | ##################################### | 100% \u001b[A\n",
306
+ " \u001b[A\n",
307
+ " \u001b[A\n",
308
+ "\n",
309
+ " \u001b[A\u001b[A\n",
310
+ "\n",
311
+ "\n",
312
+ " \u001b[A\u001b[A\u001b[A\n",
313
+ "\n",
314
+ "\n",
315
+ "\n",
316
+ " \u001b[A\u001b[A\u001b[A\u001b[A\n",
317
+ "\n",
318
+ "\n",
319
+ "\n",
320
+ "\n",
321
+ " \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
322
+ "\n",
323
+ "\n",
324
+ "\n",
325
+ "\n",
326
+ "\n",
327
+ " \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
328
+ "\n",
329
+ "\n",
330
+ "\n",
331
+ "\n",
332
+ "\n",
333
+ "\n",
334
+ " \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
335
+ "\n",
336
+ "\n",
337
+ "\n",
338
+ "\n",
339
+ "\n",
340
+ "\n",
341
+ "\n",
342
+ " \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
343
+ "Preparing transaction: done\n",
344
+ "Verifying transaction: done\n",
345
+ "Executing transaction: done\n",
346
+ "Collecting package metadata (current_repodata.json): / WARNING conda.models.version:get_matcher(556): Using .* with relational operator is superfluous and deprecated and will be removed in a future version of conda. Your spec was 1.7.1.*, but conda is ignoring the .* and treating it as 1.7.1\n",
347
+ "done\n",
348
+ "Solving environment: done\n",
349
+ "\n",
350
+ "\n",
351
+ "==> WARNING: A newer version of conda exists. <==\n",
352
+ " current version: 23.9.0\n",
353
+ " latest version: 24.1.2\n",
354
+ "\n",
355
+ "Please update conda by running\n",
356
+ "\n",
357
+ " $ conda update -n base -c defaults conda\n",
358
+ "\n",
359
+ "Or to minimize the number of packages updated during conda update use\n",
360
+ "\n",
361
+ " conda install conda=24.1.2\n",
362
+ "\n",
363
+ "\n",
364
+ "\n",
365
+ "## Package Plan ##\n",
366
+ "\n",
367
+ " environment location: /opt/conda\n",
368
+ "\n",
369
+ " added / updated specs:\n",
370
+ " - git-lfs\n",
371
+ "\n",
372
+ "\n",
373
+ "The following packages will be downloaded:\n",
374
+ "\n",
375
+ " package | build\n",
376
+ " ---------------------------|-----------------\n",
377
+ " ca-certificates-2024.2.2 | hbcca054_0 152 KB conda-forge\n",
378
+ " certifi-2024.2.2 | pyhd8ed1ab_0 157 KB conda-forge\n",
379
+ " git-lfs-3.4.1 | ha770c72_0 3.6 MB conda-forge\n",
380
+ " openssl-3.0.13 | h7f8727e_0 5.2 MB\n",
381
+ " ------------------------------------------------------------\n",
382
+ " Total: 9.1 MB\n",
383
+ "\n",
384
+ "The following NEW packages will be INSTALLED:\n",
385
+ "\n",
386
+ " git-lfs conda-forge/linux-64::git-lfs-3.4.1-ha770c72_0 \n",
387
+ "\n",
388
+ "The following packages will be UPDATED:\n",
389
+ "\n",
390
+ " ca-certificates anaconda::ca-certificates-2023.08.22-~ --> conda-forge::ca-certificates-2024.2.2-hbcca054_0 \n",
391
+ " certifi anaconda/linux-64::certifi-2023.11.17~ --> conda-forge/noarch::certifi-2024.2.2-pyhd8ed1ab_0 \n",
392
+ " openssl anaconda::openssl-3.0.12-h7f8727e_0 --> pkgs/main::openssl-3.0.13-h7f8727e_0 \n",
393
+ "\n",
394
+ "\n",
395
+ "\n",
396
+ "Downloading and Extracting Packages:\n",
397
+ "certifi-2024.2.2 | 157 KB | | 0% \n",
398
+ "git-lfs-3.4.1 | 3.6 MB | | 0% \u001b[A\n",
399
+ "\n",
400
+ "openssl-3.0.13 | 5.2 MB | | 0% \u001b[A\u001b[A\n",
401
+ "\n",
402
+ "\n",
403
+ "ca-certificates-2024 | 152 KB | | 0% \u001b[A\u001b[A\u001b[A\n",
404
+ "\n",
405
+ "certifi-2024.2.2 | 157 KB | ###7 | 10% \u001b[A\u001b[A\n",
406
+ "\n",
407
+ "\n",
408
+ "ca-certificates-2024 | 152 KB | ###9 | 11% \u001b[A\u001b[A\u001b[A\n",
409
+ "git-lfs-3.4.1 | 3.6 MB | 1 | 0% \u001b[A\n",
410
+ "\n",
411
+ "\n",
412
+ "certifi-2024.2.2 | 157 KB | ##################################### | 100% \u001b[A\u001b[A\u001b[A\n",
413
+ "\n",
414
+ "openssl-3.0.13 | 5.2 MB | ################ | 43% \u001b[A\u001b[A\n",
415
+ "git-lfs-3.4.1 | 3.6 MB | ##############5 | 39% \u001b[A\n",
416
+ "git-lfs-3.4.1 | 3.6 MB | ##################################### | 100% \u001b[A\n",
417
+ "git-lfs-3.4.1 | 3.6 MB | ##################################### | 100% \u001b[A\n",
418
+ "\n",
419
+ "openssl-3.0.13 | 5.2 MB | ##################################### | 100% \u001b[A\u001b[A\n",
420
+ "\n",
421
+ " \u001b[A\u001b[A\n",
422
+ " \u001b[A\n",
423
+ "\n",
424
+ " \u001b[A\u001b[A\n",
425
+ "\n",
426
+ "\n",
427
+ " \u001b[A\u001b[A\u001b[A\n",
428
+ "Preparing transaction: done\n",
429
+ "Verifying transaction: done\n",
430
+ "Executing transaction: done\n",
431
+ "Git LFS initialized.\n",
432
+ "Installation completed.\n"
433
+ ]
434
+ }
435
+ ],
436
+ "source": [
437
+ "import sys\n",
438
+ "\n",
439
+ "# Install git\n",
440
+ "!conda install -c anaconda git -y\n",
441
+ "\n",
442
+ "# Install git-lfs\n",
443
+ "!conda install -c conda-forge git-lfs -y\n",
444
+ "\n",
445
+ "# Set up git-lfs (you only need to do this once)\n",
446
+ "!git lfs install\n",
447
+ "\n",
448
+ "print(\"Installation completed.\")"
449
+ ]
450
+ },
451
+ {
452
+ "cell_type": "code",
453
+ "execution_count": 8,
454
+ "id": "785e2b01-4046-4aac-b72b-3918ab723414",
455
+ "metadata": {
456
+ "scrolled": true
457
+ },
458
+ "outputs": [
459
+ {
460
+ "name": "stderr",
461
+ "output_type": "stream",
462
+ "text": [
463
+ "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'Repository' (from 'huggingface_hub.repository') is deprecated and will be removed from version '1.0'. Please prefer the http-based alternatives instead. Given its large adoption in legacy code, the complete removal is only planned on next major release.\n",
464
+ "For more details, please read https://huggingface.co/docs/huggingface_hub/concepts/git_vs_http.\n",
465
+ " warnings.warn(warning_message, FutureWarning)\n"
466
+ ]
467
+ },
468
+ {
469
+ "ename": "ValueError",
470
+ "evalue": "If not specifying `clone_from`, you need to pass Repository a valid git clone.",
471
+ "output_type": "error",
472
+ "traceback": [
473
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
474
+ "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
475
+ "Cell \u001b[0;32mIn[8], line 33\u001b[0m\n\u001b[1;32m 31\u001b[0m repo \u001b[38;5;241m=\u001b[39m Repository(local_dir\u001b[38;5;241m=\u001b[39mrepo_local_path, clone_from\u001b[38;5;241m=\u001b[39mrepo_url, use_auth_token\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 32\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 33\u001b[0m repo \u001b[38;5;241m=\u001b[39m \u001b[43mRepository\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlocal_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_local_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 34\u001b[0m repo\u001b[38;5;241m.\u001b[39mgit_pull()\n\u001b[1;32m 36\u001b[0m \u001b[38;5;66;03m# Copy files from your model directory to the cloned repository\u001b[39;00m\n",
476
+ "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:118\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 115\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[1;32m 116\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
477
+ "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:132\u001b[0m, in \u001b[0;36m_deprecate_method.<locals>._inner_deprecate_method.<locals>.inner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 130\u001b[0m warning_message \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m message\n\u001b[1;32m 131\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(warning_message, \u001b[38;5;167;01mFutureWarning\u001b[39;00m)\n\u001b[0;32m--> 132\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
478
+ "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/huggingface_hub/repository.py:538\u001b[0m, in \u001b[0;36mRepository.__init__\u001b[0;34m(self, local_dir, clone_from, repo_type, token, git_user, git_email, revision, skip_lfs_files, client)\u001b[0m\n\u001b[1;32m 536\u001b[0m logger\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[Repository] is a valid git repo\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 537\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 538\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIf not specifying `clone_from`, you need to pass Repository a valid git clone.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 540\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhuggingface_token \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m (git_email \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mor\u001b[39;00m git_user \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 541\u001b[0m user \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclient\u001b[38;5;241m.\u001b[39mwhoami(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhuggingface_token)\n",
479
+ "\u001b[0;31mValueError\u001b[0m: If not specifying `clone_from`, you need to pass Repository a valid git clone."
480
+ ]
481
+ }
482
+ ],
483
+ "source": [
484
+ "from huggingface_hub import HfApi, HfFolder, Repository\n",
485
+ "import os\n",
486
+ "\n",
487
+ "# Define the path to your model and the name of the Hugging Face repository\n",
488
+ "local_model_directory = \"./workspace/outputs/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/a83a8c0d-5838-47ac-ba15-69da87e94619/epoch_3/step_final/\"\n",
489
+ "repo_name = \"clau_creat\"\n",
490
+ "username = \"arthrod\" # Replace with your Hugging Face username\n",
491
+ "repo_id = f\"{username}/{repo_name}\"\n",
492
+ "\n",
493
+ "# Authenticate with Hugging Face\n",
494
+ "#token = HfFolder.get_token()\n",
495
+ "#if token is None:\n",
496
+ "# raise ValueError(\"You must be logged in to Hugging Face. Use `huggingface-cli login`.\")\n",
497
+ "\n",
498
+ "# Initialize the HfApi object\n",
499
+ "api = HfApi()\n",
500
+ "\n",
501
+ "# Check if the repository exists, if not, create it\n",
502
+ "try:\n",
503
+ " api.repo_info(repo_id=repo_id)\n",
504
+ "except Exception as e:\n",
505
+ " print(f\"Repository {repo_id} does not exist. Creating it...\")\n",
506
+ " api.create_repo(token=token, name=repo_name, organization=username, private=False) # Set private=True for a private repository\n",
507
+ "\n",
508
+ "# Clone the repository (if necessary) and copy your model files into it\n",
509
+ "repo_url = f\"https://huggingface.co/{repo_id}\"\n",
510
+ "repo_local_path = os.path.join(os.getcwd(), repo_name)\n",
511
+ "\n",
512
+ "# If the repo directory doesn't exist, clone it. Otherwise, just pull the latest changes\n",
513
+ "if not os.path.isdir(repo_local_path):\n",
514
+ " repo = Repository(local_dir=repo_local_path, clone_from=repo_url, use_auth_token=True)\n",
515
+ "else:\n",
516
+ " repo = Repository(local_dir=repo_local_path, use_auth_token=True)\n",
517
+ " repo.git_pull()\n",
518
+ "\n",
519
+ "# Copy files from your model directory to the cloned repository\n",
520
+ "for file_name in os.listdir(local_model_directory):\n",
521
+ " src_file_path = os.path.join(local_model_directory, file_name)\n",
522
+ " dst_file_path = os.path.join(repo_local_path, file_name)\n",
523
+ " if os.path.isfile(src_file_path):\n",
524
+ " os.replace(src_file_path, dst_file_path)\n",
525
+ "\n",
526
+ "# Commit and push the changes to the repository\n",
527
+ "repo.git_add(auto_lfs_track=True)\n",
528
+ "repo.git_commit(\"Upload model to Hugging Face Hub\")\n",
529
+ "repo.git_push()\n",
530
+ "\n",
531
+ "print(f\"Model successfully uploaded to: https://huggingface.co/{repo_id}\")"
532
+ ]
533
+ },
534
+ {
535
+ "cell_type": "code",
536
+ "execution_count": 14,
537
+ "id": "41eb533d-7d4b-45a6-ae1a-e6cab2275431",
538
+ "metadata": {},
539
+ "outputs": [
540
+ {
541
+ "name": "stdout",
542
+ "output_type": "stream",
543
+ "text": [
544
+ "Collecting pickleshare\n",
545
+ " Downloading pickleshare-0.7.5-py2.py3-none-any.whl.metadata (1.5 kB)\n",
546
+ "Downloading pickleshare-0.7.5-py2.py3-none-any.whl (6.9 kB)\n",
547
+ "Installing collected packages: pickleshare\n",
548
+ "Successfully installed pickleshare-0.7.5\n",
549
+ "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
550
+ "\u001b[0m"
551
+ ]
552
+ }
553
+ ],
554
+ "source": [
555
+ "!pip install pickleshare"
556
+ ]
557
+ },
558
+ {
559
+ "cell_type": "code",
560
+ "execution_count": 16,
561
+ "id": "c6d17b7a-fb51-4e10-83b6-c47c4eabdf36",
562
+ "metadata": {},
563
+ "outputs": [
564
+ {
565
+ "name": "stdout",
566
+ "output_type": "stream",
567
+ "text": [
568
+ "[Errno 2] No such file or directory: '/outputs/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/a83a8c0d-5838-47ac-ba15-69da87e94619/epoch_3/step_final'\n",
569
+ "/workspace/outputs/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/a83a8c0d-5838-47ac-ba15-69da87e94619/epoch_3\n"
570
+ ]
571
+ }
572
+ ],
573
+ "source": [
574
+ "%cd /outputs/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/a83a8c0d-5838-47ac-ba15-69da87e94619/epoch_3/step_final"
575
+ ]
576
+ },
577
+ {
578
+ "cell_type": "code",
579
+ "execution_count": 17,
580
+ "id": "9e644c65-2937-42a6-b7b4-658f763b2b3a",
581
+ "metadata": {},
582
+ "outputs": [
583
+ {
584
+ "name": "stdout",
585
+ "output_type": "stream",
586
+ "text": [
587
+ "/workspace/outputs/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/a83a8c0d-5838-47ac-ba15-69da87e94619/epoch_3\n"
588
+ ]
589
+ }
590
+ ],
591
+ "source": [
592
+ "!pwd"
593
+ ]
594
+ },
595
+ {
596
+ "cell_type": "code",
597
+ "execution_count": null,
598
+ "id": "be54ebe7-5970-46d2-b5dd-61da9670b1d9",
599
+ "metadata": {},
600
+ "outputs": [
601
+ {
602
+ "data": {
603
+ "application/vnd.jupyter.widget-view+json": {
604
+ "model_id": "83b5e3d4e3c34a7ea9f2ef61e59af30a",
605
+ "version_major": 2,
606
+ "version_minor": 0
607
+ },
608
+ "text/plain": [
609
+ "Upload 3 LFS files: 0%| | 0/3 [00:00<?, ?it/s]"
610
+ ]
611
+ },
612
+ "metadata": {},
613
+ "output_type": "display_data"
614
+ },
615
+ {
616
+ "data": {
617
+ "application/vnd.jupyter.widget-view+json": {
618
+ "model_id": "3cf26060d2354c9391518f745d9015fd",
619
+ "version_major": 2,
620
+ "version_minor": 0
621
+ },
622
+ "text/plain": [
623
+ "tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s]"
624
+ ]
625
+ },
626
+ "metadata": {},
627
+ "output_type": "display_data"
628
+ },
629
+ {
630
+ "data": {
631
+ "application/vnd.jupyter.widget-view+json": {
632
+ "model_id": "541431de504e420eb35dda77b7de8a3c",
633
+ "version_major": 2,
634
+ "version_minor": 0
635
+ },
636
+ "text/plain": [
637
+ "pytorch_model-00001-of-00002.bin: 0%| | 0.00/9.94G [00:00<?, ?B/s]"
638
+ ]
639
+ },
640
+ "metadata": {},
641
+ "output_type": "display_data"
642
+ },
643
+ {
644
+ "data": {
645
+ "application/vnd.jupyter.widget-view+json": {
646
+ "model_id": "24f509ed004745fba85a9e250bb6cd05",
647
+ "version_major": 2,
648
+ "version_minor": 0
649
+ },
650
+ "text/plain": [
651
+ "pytorch_model-00002-of-00002.bin: 0%| | 0.00/4.54G [00:00<?, ?B/s]"
652
+ ]
653
+ },
654
+ "metadata": {},
655
+ "output_type": "display_data"
656
+ }
657
+ ],
658
+ "source": [
659
+ "from huggingface_hub import HfApi, HfFolder\n",
660
+ "import os\n",
661
+ "\n",
662
+ "def upload_files_to_hub(directory, repo_name, username, private=False):\n",
663
+ " \"\"\"\n",
664
+ " Uploads files from a specified directory to a Hugging Face Hub repository using the HTTP-based API.\n",
665
+ "\n",
666
+ " Parameters:\n",
667
+ " - directory: The local directory where your files are stored.\n",
668
+ " - repo_name: The name of the repository on the Hugging Face Hub.\n",
669
+ " - username: Your Hugging Face username.\n",
670
+ " - private: (Optional) Whether to create a private repository. Defaults to False.\n",
671
+ " \"\"\"\n",
672
+ " # Ensure the directory is an absolute path\n",
673
+ " directory = os.path.abspath(directory)\n",
674
+ "\n",
675
+ " # Instantiate HfApi object\n",
676
+ " api = HfApi()\n",
677
+ "\n",
678
+ " # Get token\n",
679
+ " token = HfFolder.get_token()\n",
680
+ " if token is None:\n",
681
+ " raise ValueError(\"You must be logged in to Hugging Face. Use `huggingface-cli login`.\")\n",
682
+ "\n",
683
+ " # Correctly specify the repository ID\n",
684
+ " repo_id = f\"{username}/{repo_name}\"\n",
685
+ "\n",
686
+ " # Check if the repository exists, and create it if it does not\n",
687
+ " try:\n",
688
+ " repo_url = api.create_repo(token=token, repo_id=repo_id, private=private, exist_ok=True)\n",
689
+ " except Exception as e:\n",
690
+ " print(f\"Error creating repository: {e}\")\n",
691
+ " return\n",
692
+ "\n",
693
+ " # Upload directory to repository\n",
694
+ " try:\n",
695
+ " api.upload_folder(token=token, repo_id=repo_id, folder_path=directory, path_in_repo=\"\")\n",
696
+ " print(f\"Files successfully uploaded to: {repo_url}\")\n",
697
+ " except Exception as e:\n",
698
+ " print(f\"Error uploading files to the repository: {e}\")\n",
699
+ "\n",
700
+ "# Example usage\n",
701
+ "upload_files_to_hub(directory=\".\", repo_name=\"clau_creat\", username=\"arthrod\", private=False)"
702
+ ]
703
+ },
704
+ {
705
+ "cell_type": "code",
706
+ "execution_count": null,
707
+ "id": "a93ce8ca-1e47-4dfb-b8d7-7ebec869f842",
708
+ "metadata": {},
709
+ "outputs": [],
710
+ "source": []
711
+ }
712
+ ],
713
+ "metadata": {
714
+ "kernelspec": {
715
+ "display_name": "Python 3 (ipykernel)",
716
+ "language": "python",
717
+ "name": "python3"
718
+ },
719
+ "language_info": {
720
+ "codemirror_mode": {
721
+ "name": "ipython",
722
+ "version": 3
723
+ },
724
+ "file_extension": ".py",
725
+ "mimetype": "text/x-python",
726
+ "name": "python",
727
+ "nbconvert_exporter": "python",
728
+ "pygments_lexer": "ipython3",
729
+ "version": "3.10.13"
730
+ }
731
+ },
732
+ "nbformat": 4,
733
+ "nbformat_minor": 5
734
+ }
step_final/added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|im_end|>": 32000,
6
+ "<|im_start|>": 32001,
7
+ "<|pad|>": 32002
8
+ }
step_final/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.34.0",
24
+ "use_cache": false,
25
+ "vocab_size": 32003
26
+ }
step_final/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "transformers_version": "4.34.0"
6
+ }
step_final/pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295e57e2d26f14808cc39b75074bf3e795ebc51132b54a7017ff5914e7c59cd0
3
+ size 9943057459
step_final/pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20775b945fad4e0455de876dea2c812ef5b0a4227c01eef426202bbe7ba3c878
3
+ size 4540562694
step_final/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483513344
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
297
+ }
298
+ }
step_final/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "<|im_end|>",
7
+ "<|im_start|>"
8
+ ],
9
+ "bos_token": "<s>",
10
+ "eos_token": "<|im_end|>",
11
+ "pad_token": "<|pad|>",
12
+ "unk_token": "<unk>"
13
+ }
step_final/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
step_final/tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|pad|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<unk>",
56
+ "<s>",
57
+ "</s>",
58
+ "<|im_end|>",
59
+ "<|im_start|>"
60
+ ],
61
+ "bos_token": "<s>",
62
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
63
+ "clean_up_tokenization_spaces": false,
64
+ "eos_token": "<|im_end|>",
65
+ "legacy": true,
66
+ "model_max_length": 2048,
67
+ "pad_token": "<|pad|>",
68
+ "padding_side": "right",
69
+ "sp_model_kwargs": {},
70
+ "spaces_between_special_tokens": false,
71
+ "tokenizer_class": "LlamaTokenizer",
72
+ "tokenizer_file": null,
73
+ "trust_remote_code": false,
74
+ "unk_token": "<unk>",
75
+ "use_default_system_prompt": true,
76
+ "use_fast": true
77
+ }