Hugging Face's logo

aegon-h
/
Huginn-13B-GPT

Text Generation
Transformers
PyTorch
llama
text-generation-inference
4-bit precision
gptq
Model card Files
xet
 Community
Agon H commited on
Commit
41f0fa9
·
1 Parent(s): 108ccfc

Upload run this model.ipynb

Browse files
Files changed (1) hide show
  1. run this model.ipynb +326 -0
run this model.ipynb ADDED
@@ -0,0 +1,326 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 1,
6
+ "id": "aba711ad-331a-4c27-b732-be5886f70599",
7
+ "metadata": {
8
+ "tags": []
9
+ },
10
+ "outputs": [],
11
+ "source": [
12
+ "!pip install -q -U transformers peft accelerate optimum"
13
+ ]
14
+ },
15
+ {
16
+ "cell_type": "code",
17
+ "execution_count": 2,
18
+ "id": "2fa956a0-882e-4df7-8af4-30a91efb1fb2",
19
+ "metadata": {
20
+ "tags": []
21
+ },
22
+ "outputs": [
23
+ {
24
+ "name": "stdout",
25
+ "output_type": "stream",
26
+ "text": [
27
+ "Requirement already satisfied: auto-gptq in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (0.4.2+cu117)\n",
28
+ "Requirement already satisfied: accelerate>=0.19.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (0.22.0)\n",
29
+ "Requirement already satisfied: torch>=1.13.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (2.0.1)\n",
30
+ "Requirement already satisfied: transformers>=4.31.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (4.32.1)\n",
31
+ "Requirement already satisfied: datasets in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (2.14.4)\n",
32
+ "Requirement already satisfied: peft in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (0.5.0)\n",
33
+ "Requirement already satisfied: numpy in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (1.25.2)\n",
34
+ "Requirement already satisfied: rouge in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (1.0.1)\n",
35
+ "Requirement already satisfied: safetensors in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from auto-gptq) (0.3.3)\n",
36
+ "Requirement already satisfied: psutil in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from accelerate>=0.19.0->auto-gptq) (5.9.5)\n",
37
+ "Requirement already satisfied: pyyaml in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from accelerate>=0.19.0->auto-gptq) (6.0)\n",
38
+ "Requirement already satisfied: packaging>=20.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from accelerate>=0.19.0->auto-gptq) (23.1)\n",
39
+ "Requirement already satisfied: filelock in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (3.12.3)\n",
40
+ "Requirement already satisfied: nvidia-cuda-cupti-cu11==11.7.101 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.7.101)\n",
41
+ "Requirement already satisfied: nvidia-cusparse-cu11==11.7.4.91 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.7.4.91)\n",
42
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.7.99)\n",
43
+ "Requirement already satisfied: nvidia-nccl-cu11==2.14.3 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (2.14.3)\n",
44
+ "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.7.99)\n",
45
+ "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.10.3.66)\n",
46
+ "Requirement already satisfied: sympy in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (1.12)\n",
47
+ "Requirement already satisfied: nvidia-cusolver-cu11==11.4.0.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.4.0.1)\n",
48
+ "Requirement already satisfied: jinja2 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (3.1.2)\n",
49
+ "Requirement already satisfied: networkx in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (3.1)\n",
50
+ "Requirement already satisfied: typing-extensions in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (4.7.1)\n",
51
+ "Requirement already satisfied: nvidia-nvtx-cu11==11.7.91 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (11.7.91)\n",
52
+ "Requirement already satisfied: nvidia-cufft-cu11==10.9.0.58 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (10.9.0.58)\n",
53
+ "Requirement already satisfied: triton==2.0.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (2.0.0)\n",
54
+ "Requirement already satisfied: nvidia-curand-cu11==10.2.10.91 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (10.2.10.91)\n",
55
+ "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from torch>=1.13.0->auto-gptq) (8.5.0.96)\n",
56
+ "Requirement already satisfied: wheel in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.13.0->auto-gptq) (0.41.1)\n",
57
+ "Requirement already satisfied: setuptools in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.13.0->auto-gptq) (68.0.0)\n",
58
+ "Requirement already satisfied: lit in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from triton==2.0.0->torch>=1.13.0->auto-gptq) (16.0.6)\n",
59
+ "Requirement already satisfied: cmake in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from triton==2.0.0->torch>=1.13.0->auto-gptq) (3.27.2)\n",
60
+ "Requirement already satisfied: tqdm>=4.27 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from transformers>=4.31.0->auto-gptq) (4.66.1)\n",
61
+ "Requirement already satisfied: regex!=2019.12.17 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from transformers>=4.31.0->auto-gptq) (2023.8.8)\n",
62
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.15.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from transformers>=4.31.0->auto-gptq) (0.16.4)\n",
63
+ "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from transformers>=4.31.0->auto-gptq) (0.13.3)\n",
64
+ "Requirement already satisfied: requests in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from transformers>=4.31.0->auto-gptq) (2.31.0)\n",
65
+ "Requirement already satisfied: fsspec in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from huggingface-hub<1.0,>=0.15.1->transformers>=4.31.0->auto-gptq) (2023.6.0)\n",
66
+ "Requirement already satisfied: multiprocess in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from datasets->auto-gptq) (0.70.15)\n",
67
+ "Requirement already satisfied: dill<0.3.8,>=0.3.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from datasets->auto-gptq) (0.3.7)\n",
68
+ "Requirement already satisfied: aiohttp in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from datasets->auto-gptq) (3.8.5)\n",
69
+ "Requirement already satisfied: xxhash in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from datasets->auto-gptq) (3.3.0)\n",
70
+ "Requirement already satisfied: pyarrow>=8.0.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from datasets->auto-gptq) (13.0.0)\n",
71
+ "Requirement already satisfied: pandas in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from datasets->auto-gptq) (2.1.0)\n",
72
+ "Requirement already satisfied: multidict<7.0,>=4.5 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (6.0.4)\n",
73
+ "Requirement already satisfied: attrs>=17.3.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (23.1.0)\n",
74
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (4.0.3)\n",
75
+ "Requirement already satisfied: aiosignal>=1.1.2 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (1.3.1)\n",
76
+ "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (3.2.0)\n",
77
+ "Requirement already satisfied: frozenlist>=1.1.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (1.4.0)\n",
78
+ "Requirement already satisfied: yarl<2.0,>=1.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from aiohttp->datasets->auto-gptq) (1.9.2)\n",
79
+ "Requirement already satisfied: idna<4,>=2.5 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from requests->transformers>=4.31.0->auto-gptq) (3.4)\n",
80
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from requests->transformers>=4.31.0->auto-gptq) (2.0.4)\n",
81
+ "Requirement already satisfied: certifi>=2017.4.17 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from requests->transformers>=4.31.0->auto-gptq) (2023.7.22)\n",
82
+ "Requirement already satisfied: MarkupSafe>=2.0 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from jinja2->torch>=1.13.0->auto-gptq) (2.1.3)\n",
83
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from pandas->datasets->auto-gptq) (2.8.2)\n",
84
+ "Requirement already satisfied: pytz>=2020.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from pandas->datasets->auto-gptq) (2023.3)\n",
85
+ "Requirement already satisfied: tzdata>=2022.1 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from pandas->datasets->auto-gptq) (2023.3)\n",
86
+ "Requirement already satisfied: six>=1.5 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from python-dateutil>=2.8.2->pandas->datasets->auto-gptq) (1.16.0)\n",
87
+ "Requirement already satisfied: mpmath>=0.19 in /home/studio-lab-user/.conda/envs/default/lib/python3.9/site-packages (from sympy->torch>=1.13.0->auto-gptq) (1.3.0)\n"
88
+ ]
89
+ }
90
+ ],
91
+ "source": [
92
+ "!pip install auto-gptq"
93
+ ]
94
+ },
95
+ {
96
+ "cell_type": "code",
97
+ "execution_count": 3,
98
+ "id": "89705dea-d988-4ece-8073-54970626f4f7",
99
+ "metadata": {
100
+ "tags": []
101
+ },
102
+ "outputs": [
103
+ {
104
+ "data": {
105
+ "application/vnd.jupyter.widget-view+json": {
106
+ "model_id": "9540122492f14f46ba75ebce474c28b7",
107
+ "version_major": 2,
108
+ "version_minor": 0
109
+ },
110
+ "text/plain": [
111
+ "Downloading (…)lve/main/config.json: 0%| | 0.00/1.10k [00:00<?, ?B/s]"
112
+ ]
113
+ },
114
+ "metadata": {},
115
+ "output_type": "display_data"
116
+ },
117
+ {
118
+ "data": {
119
+ "application/vnd.jupyter.widget-view+json": {
120
+ "model_id": "2e25472cc600484ca211d91ca59f0d36",
121
+ "version_major": 2,
122
+ "version_minor": 0
123
+ },
124
+ "text/plain": [
125
+ "Downloading (…)fetensors.index.json: 0%| | 0.00/126k [00:00<?, ?B/s]"
126
+ ]
127
+ },
128
+ "metadata": {},
129
+ "output_type": "display_data"
130
+ },
131
+ {
132
+ "data": {
133
+ "application/vnd.jupyter.widget-view+json": {
134
+ "model_id": "b17f43950b43488ebba5a2143c02aed3",
135
+ "version_major": 2,
136
+ "version_minor": 0
137
+ },
138
+ "text/plain": [
139
+ "Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]"
140
+ ]
141
+ },
142
+ "metadata": {},
143
+ "output_type": "display_data"
144
+ },
145
+ {
146
+ "data": {
147
+ "application/vnd.jupyter.widget-view+json": {
148
+ "model_id": "0e11ede92c694293aaa5d004f7efe364",
149
+ "version_major": 2,
150
+ "version_minor": 0
151
+ },
152
+ "text/plain": [
153
+ "Downloading (…)of-00002.safetensors: 0%| | 0.00/9.98G [00:00<?, ?B/s]"
154
+ ]
155
+ },
156
+ "metadata": {},
157
+ "output_type": "display_data"
158
+ },
159
+ {
160
+ "data": {
161
+ "application/vnd.jupyter.widget-view+json": {
162
+ "model_id": "b241c5f66c854876b574739f7ba3aaba",
163
+ "version_major": 2,
164
+ "version_minor": 0
165
+ },
166
+ "text/plain": [
167
+ "Downloading (…)of-00002.safetensors: 0%| | 0.00/2.00G [00:00<?, ?B/s]"
168
+ ]
169
+ },
170
+ "metadata": {},
171
+ "output_type": "display_data"
172
+ },
173
+ {
174
+ "data": {
175
+ "application/vnd.jupyter.widget-view+json": {
176
+ "model_id": "f21bb47869cb4841b65ca603c7449453",
177
+ "version_major": 2,
178
+ "version_minor": 0
179
+ },
180
+ "text/plain": [
181
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
182
+ ]
183
+ },
184
+ "metadata": {},
185
+ "output_type": "display_data"
186
+ },
187
+ {
188
+ "data": {
189
+ "application/vnd.jupyter.widget-view+json": {
190
+ "model_id": "7154fe572cf949e38cbeaa1e212281f7",
191
+ "version_major": 2,
192
+ "version_minor": 0
193
+ },
194
+ "text/plain": [
195
+ "Downloading (…)neration_config.json: 0%| | 0.00/154 [00:00<?, ?B/s]"
196
+ ]
197
+ },
198
+ "metadata": {},
199
+ "output_type": "display_data"
200
+ },
201
+ {
202
+ "data": {
203
+ "application/vnd.jupyter.widget-view+json": {
204
+ "model_id": "426dd05bb0a743c79b9604564809a5a1",
205
+ "version_major": 2,
206
+ "version_minor": 0
207
+ },
208
+ "text/plain": [
209
+ "Downloading (…)okenizer_config.json: 0%| | 0.00/244 [00:00<?, ?B/s]"
210
+ ]
211
+ },
212
+ "metadata": {},
213
+ "output_type": "display_data"
214
+ },
215
+ {
216
+ "data": {
217
+ "application/vnd.jupyter.widget-view+json": {
218
+ "model_id": "66fab430ded94aada339c52da8cabaf7",
219
+ "version_major": 2,
220
+ "version_minor": 0
221
+ },
222
+ "text/plain": [
223
+ "Downloading tokenizer.model: 0%| | 0.00/500k [00:00<?, ?B/s]"
224
+ ]
225
+ },
226
+ "metadata": {},
227
+ "output_type": "display_data"
228
+ },
229
+ {
230
+ "data": {
231
+ "application/vnd.jupyter.widget-view+json": {
232
+ "model_id": "3b65f4ac6a764c919996c5dd750feaa0",
233
+ "version_major": 2,
234
+ "version_minor": 0
235
+ },
236
+ "text/plain": [
237
+ "Downloading (…)/main/tokenizer.json: 0%| | 0.00/1.84M [00:00<?, ?B/s]"
238
+ ]
239
+ },
240
+ "metadata": {},
241
+ "output_type": "display_data"
242
+ },
243
+ {
244
+ "data": {
245
+ "application/vnd.jupyter.widget-view+json": {
246
+ "model_id": "222828ac2eb44eefa1de3ad41cb81cf4",
247
+ "version_major": 2,
248
+ "version_minor": 0
249
+ },
250
+ "text/plain": [
251
+ "Downloading (…)in/added_tokens.json: 0%| | 0.00/21.0 [00:00<?, ?B/s]"
252
+ ]
253
+ },
254
+ "metadata": {},
255
+ "output_type": "display_data"
256
+ },
257
+ {
258
+ "data": {
259
+ "application/vnd.jupyter.widget-view+json": {
260
+ "model_id": "850fb340b7104c3a8b7d8fedda825690",
261
+ "version_major": 2,
262
+ "version_minor": 0
263
+ },
264
+ "text/plain": [
265
+ "Downloading (…)cial_tokens_map.json: 0%| | 0.00/435 [00:00<?, ?B/s]"
266
+ ]
267
+ },
268
+ "metadata": {},
269
+ "output_type": "display_data"
270
+ }
271
+ ],
272
+ "source": [
273
+ "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
274
+ "\n",
275
+ "model_id = \"agonh/MythoMax22b-Falseblock-GPT\"\n",
276
+ "model = AutoModelForCausalLM.from_pretrained(model_id, device_map=\"auto\")\n",
277
+ "tokenizer = AutoTokenizer.from_pretrained(model_id)"
278
+ ]
279
+ },
280
+ {
281
+ "cell_type": "code",
282
+ "execution_count": null,
283
+ "id": "d295d782-866a-4c60-9d03-18777a777568",
284
+ "metadata": {
285
+ "tags": []
286
+ },
287
+ "outputs": [],
288
+ "source": [
289
+ "text = \"Tell me about AI\"\n",
290
+ "inputs = tokenizer(text, return_tensors=\"pt\").to(0)\n",
291
+ "\n",
292
+ "out = model.generate(**inputs, max_new_tokens=500)\n",
293
+ "print(tokenizer.decode(out[0], skip_special_tokens=True))"
294
+ ]
295
+ },
296
+ {
297
+ "cell_type": "code",
298
+ "execution_count": null,
299
+ "id": "ea9720ad-d3ca-4a5f-8cf6-1846ea3e1e13",
300
+ "metadata": {},
301
+ "outputs": [],
302
+ "source": []
303
+ }
304
+ ],
305
+ "metadata": {
306
+ "kernelspec": {
307
+ "display_name": "default:Python",
308
+ "language": "python",
309
+ "name": "conda-env-default-py"
310
+ },
311
+ "language_info": {
312
+ "codemirror_mode": {
313
+ "name": "ipython",
314
+ "version": 3
315
+ },
316
+ "file_extension": ".py",
317
+ "mimetype": "text/x-python",
318
+ "name": "python",
319
+ "nbconvert_exporter": "python",
320
+ "pygments_lexer": "ipython3",
321
+ "version": "3.9.16"
322
+ }
323
+ },
324
+ "nbformat": 4,
325
+ "nbformat_minor": 5
326
+ }