Upload Poro_GPTQ_quantization_testing.ipynb
Browse files
Poro_GPTQ_quantization_testing.ipynb
ADDED
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "markdown",
|
5 |
+
"id": "c1741b36-a53c-44db-9384-e823f06934bf",
|
6 |
+
"metadata": {},
|
7 |
+
"source": [
|
8 |
+
"# Poro GPTQ quantization testing"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
{
|
12 |
+
"cell_type": "code",
|
13 |
+
"execution_count": 1,
|
14 |
+
"id": "5a39da1e-88f5-42a1-b00c-fa987b1fd1de",
|
15 |
+
"metadata": {
|
16 |
+
"tags": []
|
17 |
+
},
|
18 |
+
"outputs": [],
|
19 |
+
"source": [
|
20 |
+
"from transformers import AutoModelForCausalLM, AutoTokenizer"
|
21 |
+
]
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"cell_type": "code",
|
25 |
+
"execution_count": 3,
|
26 |
+
"id": "0738c247-52e4-4c22-84ef-e13c6fc2a533",
|
27 |
+
"metadata": {
|
28 |
+
"tags": []
|
29 |
+
},
|
30 |
+
"outputs": [
|
31 |
+
{
|
32 |
+
"data": {
|
33 |
+
"application/vnd.jupyter.widget-view+json": {
|
34 |
+
"model_id": "3e80cefcd53149d6bb962b6aaee3154f",
|
35 |
+
"version_major": 2,
|
36 |
+
"version_minor": 0
|
37 |
+
},
|
38 |
+
"text/plain": [
|
39 |
+
"config.json: 0%| | 0.00/1.43k [00:00<?, ?B/s]"
|
40 |
+
]
|
41 |
+
},
|
42 |
+
"metadata": {},
|
43 |
+
"output_type": "display_data"
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"data": {
|
47 |
+
"application/vnd.jupyter.widget-view+json": {
|
48 |
+
"model_id": "15a5a41816c0491cb17e15b722d02139",
|
49 |
+
"version_major": 2,
|
50 |
+
"version_minor": 0
|
51 |
+
},
|
52 |
+
"text/plain": [
|
53 |
+
"model.safetensors.index.json: 0%| | 0.00/115k [00:00<?, ?B/s]"
|
54 |
+
]
|
55 |
+
},
|
56 |
+
"metadata": {},
|
57 |
+
"output_type": "display_data"
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"data": {
|
61 |
+
"application/vnd.jupyter.widget-view+json": {
|
62 |
+
"model_id": "d314aea93bb64a38a95f27b52fcf2957",
|
63 |
+
"version_major": 2,
|
64 |
+
"version_minor": 0
|
65 |
+
},
|
66 |
+
"text/plain": [
|
67 |
+
"Downloading shards: 0%| | 0/4 [00:00<?, ?it/s]"
|
68 |
+
]
|
69 |
+
},
|
70 |
+
"metadata": {},
|
71 |
+
"output_type": "display_data"
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"data": {
|
75 |
+
"application/vnd.jupyter.widget-view+json": {
|
76 |
+
"model_id": "fd4c51235a294532856b038346e0928c",
|
77 |
+
"version_major": 2,
|
78 |
+
"version_minor": 0
|
79 |
+
},
|
80 |
+
"text/plain": [
|
81 |
+
"model-00001-of-00004.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s]"
|
82 |
+
]
|
83 |
+
},
|
84 |
+
"metadata": {},
|
85 |
+
"output_type": "display_data"
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"data": {
|
89 |
+
"application/vnd.jupyter.widget-view+json": {
|
90 |
+
"model_id": "d0916b3277104f4c948f2884b321a3c2",
|
91 |
+
"version_major": 2,
|
92 |
+
"version_minor": 0
|
93 |
+
},
|
94 |
+
"text/plain": [
|
95 |
+
"model-00002-of-00004.safetensors: 0%| | 0.00/4.94G [00:00<?, ?B/s]"
|
96 |
+
]
|
97 |
+
},
|
98 |
+
"metadata": {},
|
99 |
+
"output_type": "display_data"
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"data": {
|
103 |
+
"application/vnd.jupyter.widget-view+json": {
|
104 |
+
"model_id": "f9f166bf7bbd461b9c01f9849b2e3fbc",
|
105 |
+
"version_major": 2,
|
106 |
+
"version_minor": 0
|
107 |
+
},
|
108 |
+
"text/plain": [
|
109 |
+
"model-00003-of-00004.safetensors: 0%| | 0.00/5.00G [00:00<?, ?B/s]"
|
110 |
+
]
|
111 |
+
},
|
112 |
+
"metadata": {},
|
113 |
+
"output_type": "display_data"
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"data": {
|
117 |
+
"application/vnd.jupyter.widget-view+json": {
|
118 |
+
"model_id": "0db3f2c91703495684eb891f59ccaa1b",
|
119 |
+
"version_major": 2,
|
120 |
+
"version_minor": 0
|
121 |
+
},
|
122 |
+
"text/plain": [
|
123 |
+
"model-00004-of-00004.safetensors: 0%| | 0.00/4.28G [00:00<?, ?B/s]"
|
124 |
+
]
|
125 |
+
},
|
126 |
+
"metadata": {},
|
127 |
+
"output_type": "display_data"
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"data": {
|
131 |
+
"application/vnd.jupyter.widget-view+json": {
|
132 |
+
"model_id": "cd662139ce2442d9b87f9c834274f790",
|
133 |
+
"version_major": 2,
|
134 |
+
"version_minor": 0
|
135 |
+
},
|
136 |
+
"text/plain": [
|
137 |
+
"Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]"
|
138 |
+
]
|
139 |
+
},
|
140 |
+
"metadata": {},
|
141 |
+
"output_type": "display_data"
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"data": {
|
145 |
+
"application/vnd.jupyter.widget-view+json": {
|
146 |
+
"model_id": "66fe78e818094b069237426c0b3bd4d7",
|
147 |
+
"version_major": 2,
|
148 |
+
"version_minor": 0
|
149 |
+
},
|
150 |
+
"text/plain": [
|
151 |
+
"generation_config.json: 0%| | 0.00/132 [00:00<?, ?B/s]"
|
152 |
+
]
|
153 |
+
},
|
154 |
+
"metadata": {},
|
155 |
+
"output_type": "display_data"
|
156 |
+
}
|
157 |
+
],
|
158 |
+
"source": [
|
159 |
+
"# Model download from Huggingface\n",
|
160 |
+
"model = AutoModelForCausalLM.from_pretrained(\"mlconvexai/Poro-34B-GPTQ-SGroup\",device_map=\"auto\")"
|
161 |
+
]
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"cell_type": "code",
|
165 |
+
"execution_count": 4,
|
166 |
+
"id": "7421bd8a-c835-4259-abfb-539fd41a0285",
|
167 |
+
"metadata": {
|
168 |
+
"tags": []
|
169 |
+
},
|
170 |
+
"outputs": [
|
171 |
+
{
|
172 |
+
"data": {
|
173 |
+
"application/vnd.jupyter.widget-view+json": {
|
174 |
+
"model_id": "6542cd3dc1d04921ae7453d2b40ad252",
|
175 |
+
"version_major": 2,
|
176 |
+
"version_minor": 0
|
177 |
+
},
|
178 |
+
"text/plain": [
|
179 |
+
"tokenizer_config.json: 0%| | 0.00/4.94k [00:00<?, ?B/s]"
|
180 |
+
]
|
181 |
+
},
|
182 |
+
"metadata": {},
|
183 |
+
"output_type": "display_data"
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"data": {
|
187 |
+
"application/vnd.jupyter.widget-view+json": {
|
188 |
+
"model_id": "24f3f3811fd145a4ba07d1f35f591005",
|
189 |
+
"version_major": 2,
|
190 |
+
"version_minor": 0
|
191 |
+
},
|
192 |
+
"text/plain": [
|
193 |
+
"tokenizer.json: 0%| | 0.00/5.64M [00:00<?, ?B/s]"
|
194 |
+
]
|
195 |
+
},
|
196 |
+
"metadata": {},
|
197 |
+
"output_type": "display_data"
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"data": {
|
201 |
+
"application/vnd.jupyter.widget-view+json": {
|
202 |
+
"model_id": "986046ba401b4377aee6e86e9c82fa1b",
|
203 |
+
"version_major": 2,
|
204 |
+
"version_minor": 0
|
205 |
+
},
|
206 |
+
"text/plain": [
|
207 |
+
"special_tokens_map.json: 0%| | 0.00/1.00k [00:00<?, ?B/s]"
|
208 |
+
]
|
209 |
+
},
|
210 |
+
"metadata": {},
|
211 |
+
"output_type": "display_data"
|
212 |
+
}
|
213 |
+
],
|
214 |
+
"source": [
|
215 |
+
"# Tokenizer download\n",
|
216 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"mlconvexai/Poro-34B-GPTQ-SGroup\", use_fast=True)"
|
217 |
+
]
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"cell_type": "code",
|
221 |
+
"execution_count": 5,
|
222 |
+
"id": "85931283-aafa-48c7-b3dc-e63151cbb88c",
|
223 |
+
"metadata": {
|
224 |
+
"tags": []
|
225 |
+
},
|
226 |
+
"outputs": [],
|
227 |
+
"source": [
|
228 |
+
"# Example prompt and input preparation\n",
|
229 |
+
"prompt = 'Given the question delimited by triple backticks ```{ Kuinka vaihdan uutiskirjeen sähköpostiosoitteen? }```, what is the answer? Answer:'"
|
230 |
+
]
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"cell_type": "code",
|
234 |
+
"execution_count": 6,
|
235 |
+
"id": "91d7d540-214d-46cd-bca8-e20b67c9f298",
|
236 |
+
"metadata": {
|
237 |
+
"tags": []
|
238 |
+
},
|
239 |
+
"outputs": [],
|
240 |
+
"source": [
|
241 |
+
"input_ids = tokenizer(prompt, return_tensors='pt').input_ids.cuda()"
|
242 |
+
]
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"cell_type": "code",
|
246 |
+
"execution_count": 7,
|
247 |
+
"id": "e8afd403-3289-4371-a9ba-06d9149a95fc",
|
248 |
+
"metadata": {
|
249 |
+
"tags": []
|
250 |
+
},
|
251 |
+
"outputs": [],
|
252 |
+
"source": [
|
253 |
+
"# Prediction\n",
|
254 |
+
"output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)"
|
255 |
+
]
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"cell_type": "code",
|
259 |
+
"execution_count": 8,
|
260 |
+
"id": "566cfee1-8eb8-4b0e-8eba-7de3b33d3c36",
|
261 |
+
"metadata": {
|
262 |
+
"tags": []
|
263 |
+
},
|
264 |
+
"outputs": [
|
265 |
+
{
|
266 |
+
"name": "stdout",
|
267 |
+
"output_type": "stream",
|
268 |
+
"text": [
|
269 |
+
"Given the question delimited by triple backticks ```{ Kuinka vaihdan uutiskirjeen sähköpostiosoitteen? }```, what is the answer? Answer: {Kun olet tilannut uutiskirjeen, voit vaihtaa sähköpostiosoitteen itse kirjautumalla asiakastilillesi.} Given the triple backGiven the question delimited by triple backticks ```{ Miksi en saa tilattua uutiskirjettä? }```, what is the answer? Answer: {Jos et saa tilattua uutiskirjettä, voit tarkistaa, että olet antanut oikean sähköpostiosoitteen. Mikäli et edelleenkään saa tilattua uutiskirjettä, ota yhteyttä asiakaspalveluumme.} Given the triple backGiven the question delimited by triple backticks ```{ Mihin sähköpostiosoitteeseen uutiskirje lähetetään? }```, what is the answer? Answer: {Uutiskirje lähetetään siihen sähköpostiosoitteeseen, jonka olet antanut tilauksen yhteydessä.}\n",
|
270 |
+
"\n",
|
271 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Mitä tietoja uutiskirjeen tilaaja saa?}```, what is the answer? Answer: {Uutiskirjeen tilaajana saat tietoa tuotteistamme, eduistamme sekä palveluistamme.}\n",
|
272 |
+
"\n",
|
273 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Miten saan peruttua uutiskirjeen?}```, what is the answer? Answer: {Uutiskirjeen voi peruuttaa jokaisessa uutiskirjeessä olevan linkin kautta.}\n",
|
274 |
+
"\n",
|
275 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Mistä näen omat tilaukseni?}```, what is the answer? Answer: {Omat tilauksesi näet asiakastililläsi.}\n",
|
276 |
+
"\n",
|
277 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Miten voin tarkistaa tilaushistoriani?}```, what is the answer? Answer: {Voit tarkistaa tilaushistoriasi asiakastililtäsi.}\n",
|
278 |
+
"\n",
|
279 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Miten voin muuttaa tai perua tilaukseni?}```, what is the answer? Answer: {Tilauksen voi muuttaa tai perua ottamalla yhteyttä asiakaspalveluumme.}\n",
|
280 |
+
"\n",
|
281 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Miten voin perua tilaukseni?}```, what is the answer? Answer: {Tilauksen voi perua ottamalla yhteyttä asiakaspalveluumme.}\n",
|
282 |
+
"\n",
|
283 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Mitä maksutapoja on käytössä?}```, what is the answer? Answer: {Käytössä ovat yleisimmät verkkopankit ja luottokortit (Visa, Mastercard), MobilePay, Jousto, Collect@Net sekä Klarna-lasku.}\n",
|
284 |
+
"\n",
|
285 |
+
"Given the triple backGiven the question delimited by triple backticks ```{ Miten voin muuttaa laskutusosoitettani?}```, what is the answer? Answer: {Laskutusosoitteen voi muuttaa ottamalla\n"
|
286 |
+
]
|
287 |
+
}
|
288 |
+
],
|
289 |
+
"source": [
|
290 |
+
"print(tokenizer.decode(output[0]))"
|
291 |
+
]
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"cell_type": "code",
|
295 |
+
"execution_count": null,
|
296 |
+
"id": "ff4406b0-5cd7-4a91-ad0f-28e71e075db8",
|
297 |
+
"metadata": {},
|
298 |
+
"outputs": [],
|
299 |
+
"source": []
|
300 |
+
}
|
301 |
+
],
|
302 |
+
"metadata": {
|
303 |
+
"environment": {
|
304 |
+
"kernel": "poro",
|
305 |
+
"name": "common-cu121.m118",
|
306 |
+
"type": "gcloud",
|
307 |
+
"uri": "us-docker.pkg.dev/deeplearning-platform-release/gcr.io/base-cu121:m118"
|
308 |
+
},
|
309 |
+
"kernelspec": {
|
310 |
+
"display_name": "Python 3",
|
311 |
+
"language": "python",
|
312 |
+
"name": "python3"
|
313 |
+
},
|
314 |
+
"language_info": {
|
315 |
+
"codemirror_mode": {
|
316 |
+
"name": "ipython",
|
317 |
+
"version": 3
|
318 |
+
},
|
319 |
+
"file_extension": ".py",
|
320 |
+
"mimetype": "text/x-python",
|
321 |
+
"name": "python",
|
322 |
+
"nbconvert_exporter": "python",
|
323 |
+
"pygments_lexer": "ipython3",
|
324 |
+
"version": "3.8.8"
|
325 |
+
}
|
326 |
+
},
|
327 |
+
"nbformat": 4,
|
328 |
+
"nbformat_minor": 5
|
329 |
+
}
|