wassname/peft
1
0
Fork 0
mirror of https://github.com/wassname/peft.git synced 2026-09-09 11:28:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix more examples

Browse Source
This commit is contained in:
Sourab Mangrulkar
2023-02-08 18:40:57 +05:30
parent afb171eefb
commit 3cf0b7a2d4
6 changed files with 1507 additions and 4337 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/causal_language_modeling/peft_lora_clm_accelerate_big_model_inference.ipynb
+6 -396
View File
@@ -48,70 +48,10 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"id": "e1a3648b",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Found cached dataset raft (/home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "d1160ad661de452dbce6944a881a160b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84/cache-20a7622c86d80cdf.arrow\n",
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84/cache-5f1431311da05803.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Unlabeled', 'complaint', 'no complaint']\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['Tweet text', 'ID', 'Label', 'text_label'],\n",
" num_rows: 50\n",
" })\n",
" test: Dataset({\n",
" features: ['Tweet text', 'ID', 'Label', 'text_label'],\n",
" num_rows: 3399\n",
" })\n",
"})\n"
]
},
{
"data": {
"text/plain": [
"{'Tweet text': '@HMRCcustomers No this is my first job',\n",
" 'ID': 0,\n",
" 'Label': 2,\n",
" 'text_label': 'no complaint'}"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"from datasets import load_dataset\n",
"\n",
@@ -229,219 +169,10 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "2795b9d0",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "293c2191c9674123afc58cfa22c0cf57",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Running tokenizer on dataset: 0%| | 0/1 [00:00<?, ?ba/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c376f3397f574c9084946ab171f43c4f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Running tokenizer on dataset: 0%| | 0/4 [00:00<?, ?ba/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'input_ids': tensor([[ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 227985, 5484, 915, 2566, 169403, 15296, 36272,\n",
" 525, 3928, 1119, 632, 2670, 3968, 15270, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 227985, 5484, 915, 2566, 88653, 2321, 144017, 138861,\n",
" 59283, 1152, 613, 2632, 12120, 4, 5673, 1152, 32153,\n",
" 427, 36992, 15, 1152, 1400, 5065, 114438, 66455, 919,\n",
" 404, 146304, 14078, 87856, 7061, 2906, 17, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 227985, 5484,\n",
" 915, 5673, 473, 11229, 2213, 2670, 35307, 28629, 461,\n",
" 2566, 2765, 1531, 3470, 47134, 10144, 2765, 1531, 427,\n",
" 2909, 17918, 6782, 27268, 4390, 1517, 17, 3904, 632,\n",
" 267, 6497, 483, 361, 2670, 101848, 17, 32465, 9585,\n",
" 2566, 37, 2481, 2566, 37, 2481, 12384, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 227985,\n",
" 5484, 915, 2566, 15157, 4867, 14731, 165189, 2021, 769,\n",
" 11528, 7220, 35025, 530, 27937, 149533, 1965, 43435, 163255,\n",
" 1141, 3611, 17, 30655, 632, 1119, 17, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 227985, 5484,\n",
" 915, 35673, 8562, 29826, 102530, 15, 1427, 207595, 17,\n",
" 915, 12, 2550, 81623, 14282, 5715, 37623, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 227985, 5484, 915, 2566, 80, 11010, 905, 200058, 3904,\n",
" 9746, 3370, 722, 1074, 15, 1965, 600, 50713, 191765,\n",
" 4973, 34, 200008, 123467, 1306, 1427, 16198, 3262, 11700,\n",
" 35237, 12602, 1293, 8398, 530, 1999, 4346, 87843, 17,\n",
" 1594, 35367, 241792, 130376, 894, 3143, 42, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 227985, 5484, 915, 2566,\n",
" 60, 80772, 1400, 1701, 2213, 368, 12171, 67777, 613,\n",
" 267, 18210, 76252, 375, 916, 6635, 1320, 3776, 934,\n",
" 44805, 1965, 13002, 934, 17, 21, 12, 791, 727,\n",
" 1701, 2971, 267, 35307, 20845, 10172, 34, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 227985,\n",
" 5484, 915, 2566, 96186, 29756, 351, 473, 1542, 654,\n",
" 9322, 530, 368, 21851, 632, 6644, 530, 48132, 17,\n",
" 6728, 1152, 727, 7747, 3638, 1119, 34, 77658, 915,\n",
" 210]]), 'attention_mask': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])}\n",
"{'input_ids': tensor([[ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 227985, 5484, 915, 2566, 74757, 64626, 12384, 44639, 613,\n",
" 52282, 2670, 79920, 3344, 1002, 368, 17646, 14472, 8348,\n",
" 664, 718, 4, 19036, 17, 31849, 17, 6312, 76,\n",
" 44, 62470, 56, 91, 50, 14839, 21, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 227985, 5484, 915, 405, 187059,\n",
" 2256, 664, 2550, 18833, 18607, 162467, 4, 1387, 6199,\n",
" 3291, 23405, 613, 4657, 17082, 566, 3432, 368, 78851,\n",
" 1185, 61273, 23181, 1553, 15596, 212, 116057, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 227985, 5484,\n",
" 915, 39762, 2566, 22253, 6201, 75701, 15, 632, 718,\n",
" 5840, 10006, 6201, 18881, 427, 3804, 19528, 267, 158974,\n",
" 1320, 368, 10029, 632, 49666, 92, 34, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 227985, 5484, 915, 2566, 104565, 8695, 2089, 6140,\n",
" 109676, 99579, 1369, 512, 368, 4570, 54, 632, 368,\n",
" 1503, 241485, 132226, 15, 982, 727, 1152, 18100, 861,\n",
" 32596, 77597, 168154, 1306, 132226, 4346, 87843, 17, 130462,\n",
" 364, 32923, 89, 53, 8309, 20, 75, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 227985, 5484, 915, 2566,\n",
" 14173, 2960, 29906, 387, 20706, 49337, 1369, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 227985, 5484, 915, 2566, 219553, 45736,\n",
" 36876, 1713, 72, 707, 187205, 13002, 177324, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 227985, 5484, 915, 2566, 233938, 28518, 13716,\n",
" 427, 28146, 1119, 17918, 17, 236706, 368, 214997, 7555,\n",
" 48659, 5276, 21600, 343, 17, 51416, 22403, 318, 1531,\n",
" 1306, 1130, 20934, 567, 101161, 184849, 87843, 17, 1594,\n",
" 15231, 2052, 16642, 20, 7180, 80, 26, 77658, 915,\n",
" 210],\n",
" [ 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 3, 3, 3, 3, 3, 3, 3, 3, 3,\n",
" 227985, 5484, 915, 2566, 80, 2068, 479, 2566, 80,\n",
" 1376, 878, 147587, 3904, 632, 368, 6084, 65673, 78851,\n",
" 11736, 15527, 19082, 33151, 461, 17, 45575, 17887, 632,\n",
" 5219, 14216, 68870, 5967, 1841, 4346, 87843, 17, 1594,\n",
" 14512, 27, 71, 8184, 19, 290, 63748, 77658, 915,\n",
" 210]]), 'attention_mask': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],\n",
" [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]])}\n"
]
}
],
"outputs": [],
"source": [
"def test_preprocess_function(examples):\n",
" batch_size = len(examples[text_column])\n",
@@ -671,131 +402,10 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": null,
"id": "a70802a3",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 3%|██▍ | 12/425 [03:14<1:51:32, 16.20s/it]\n"
]
},
{
"data": {
"text/plain": [
"['no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'no complaintcompl',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaintcompl',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaintcompl',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaintcompl',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint']"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"model.eval()\n",
"test_preds = []\n",
examples/causal_language_modeling/peft_prefix_tuning_clm.ipynb
+278 -1478
View File
File diff suppressed because it is too large Load Diff
examples/causal_language_modeling/peft_prompt_tuning_clm.ipynb
+1190
View File
File diff suppressed because it is too large Load Diff
examples/conditional_generation/peft_lora_seq2seq_accelerate_big_model_inference.ipynb
+9 -217
View File
@@ -2,26 +2,10 @@
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "71fbfca2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"===================================BUG REPORT===================================\n",
"Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
"For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link\n",
"================================================================================\n",
"CUDA SETUP: CUDA runtime path found: /home/sourab/miniconda3/envs/ml/lib/libcudart.so\n",
"CUDA SETUP: Highest compute capability among GPUs detected: 7.5\n",
"CUDA SETUP: Detected CUDA version 117\n",
"CUDA SETUP: Loading binary /home/sourab/miniconda3/envs/ml/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda117.so...\n"
]
}
],
"outputs": [],
"source": [
"from transformers import AutoModelForSeq2SeqLM\n",
"from peft import PeftModel, PeftConfig\n",
@@ -59,70 +43,10 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "e1a3648b",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Found cached dataset raft (/home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "0bf24d09ce9642ec804aa0f208f54e1d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/2 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84/cache-20a7622c86d80cdf.arrow\n",
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84/cache-5f1431311da05803.arrow\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"['Unlabeled', 'complaint', 'no complaint']\n",
"DatasetDict({\n",
" train: Dataset({\n",
" features: ['Tweet text', 'ID', 'Label', 'text_label'],\n",
" num_rows: 50\n",
" })\n",
" test: Dataset({\n",
" features: ['Tweet text', 'ID', 'Label', 'text_label'],\n",
" num_rows: 3399\n",
" })\n",
"})\n"
]
},
{
"data": {
"text/plain": [
"{'Tweet text': '@HMRCcustomers No this is my first job',\n",
" 'ID': 0,\n",
" 'Label': 2,\n",
" 'text_label': 'no complaint'}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"from datasets import load_dataset\n",
"\n",
@@ -142,19 +66,10 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "fe12d4d3",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84/cache-ad68bb6ecb83fbb7.arrow\n",
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/ought___raft/twitter_complaints/1.1.0/79c4de1312c1e3730043f7db07179c914f48403101f7124e2fe336f6f54d9f84/cache-bc43a32cf6316354.arrow\n"
]
}
],
"outputs": [],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
"target_max_length = max([len(tokenizer(class_label)[\"input_ids\"]) for class_label in classes])\n",
@@ -291,133 +206,10 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"id": "a70802a3",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/425 [00:00<?, ?it/s]/home/sourab/transformers/src/transformers/generation/utils.py:1359: UserWarning: You are calling .generate() with the `input_ids` being on a device type different than your model's device. `input_ids` is on cpu, whereas the model is on cuda. You may experience unexpected behaviors or slower generation. Please make sure that you have put `input_ids` to the correct device by calling for example input_ids = input_ids.to('cuda') before running `.generate()`.\n",
" warnings.warn(\n",
" 3%|██▌ | 12/425 [00:20<11:57, 1.74s/it]\n"
]
},
{
"data": {
"text/plain": [
"['no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'no complaint',\n",
" 'complaint',\n",
" 'no complaint']"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"model.eval()\n",
"test_preds = []\n",
@@ -450,7 +242,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
"version": "3.10.5 (v3.10.5:f377153967, Jun 6 2022, 12:36:10) [Clang 13.0.0 (clang-1300.0.29.30)]"
},
"vscode": {
"interpreter": {
examples/lora_dreambooth/lora_dreambooth_inference.ipynb
+10 -162
View File
File diff suppressed because one or more lines are too long
examples/token_classification/peft_lora_token_cls.ipynb
+14 -2084
View File
File diff suppressed because one or more lines are too long