Model | AGIEval | GPT4All | TruthfulQA | Bigbench |
---|---|---|---|---|
zephyr-7b-spin-iter1-v0 | Error: File does not exist | Error: File does not exist | Error: File does not exist | Error: File does not exist |
Average: Error: File does not exist%
Model | AGIEval | GPT4All | TruthfulQA | Bigbench |
---|---|---|---|---|
zephyr-7b-spin-iter1-v0 | Error: File does not exist | Error: File does not exist | Error: File does not exist | Error: File does not exist |
Average: Error: File does not exist%
Model | AGIEval | GPT4All | TruthfulQA | Bigbench |
---|---|---|---|---|
zephyr-7b-spin-iter1-v0 | Error: File does not exist | Error: File does not exist | Error: File does not exist | Error: File does not exist |
Average: Error: File does not exist%
import transformers | |
from datasets import load_dataset | |
from sklearn.preprocessing import MinMaxScaler | |
import shap | |
from rubrix import TextClassificationRecord, TokenAttributions | |
import rubrix as rb |
from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
from transformers_interpret import SequenceClassificationExplainer | |
from datasets import load_dataset | |
import rubrix as rb | |
from rubrix import TokenAttributions | |
# Load Stanford sentiment treebank test set | |
dataset = load_dataset("sst", "default", split="test") |
from datasets import Dataset | |
import rubrix as rb | |
# load rubrix dataset | |
df = rb.load('unlabelled_dataset_zeroshot') | |
# inputs can be dicts to support multifield classifiers, we just use the text here. | |
df['text'] = df.inputs.transform(lambda r: r['text']) | |
# we flatten the annotations and create a dict for turning labels into numeric ids |
from transformers import AutoModelForSequenceClassification | |
from transformers import AutoTokenizer | |
from transformers import Trainer | |
# from here, it's just regular fine-tuning with 🤗 transformers | |
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased") | |
model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased", num_labels=4) | |
def tokenize_function(examples): | |
return tokenizer(examples["text"], padding="max_length", truncation=True) |
text = "I love the song Computer Love from Kraftwerk" | |
record = rb.TokenClassificationRecord( | |
text=text, | |
tokens=[t for t in text.split(' ')], | |
prediction=[("SONG", 16, 29), ("BAND", 35, 44)], | |
prediction_agent="my_ner_model_v1" | |
) | |
rb.log(record, name="ner_bands_dataset") |
from transformers import pipeline | |
from datasets import load_dataset | |
import rubrix as rb | |
model = pipeline('zero-shot-classification', model="typeform/squeezebert-mnli") | |
dataset = load_dataset("ag_news", split='test') | |
# Labels are: 'World', 'Sports', 'Business', 'Sci/Tech' | |
labels = dataset.features["label"].names | |
for example in dataset: |
@base <https://www.food.com/recipe/> . | |
@prefix ind: <http://purl.org/heals/ingredient/> . | |
@prefix skos: <http://www.w3.org/2004/02/skos/core#> . | |
@prefix wtm: <http://purl.org/heals/food/> . | |
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> . | |
ind:Almond a wtm:Ingredient ; | |
skos:definition "the nutlike kernel of the fruit of either of two trees, Prunus dulcis (sweet almond) or P. dulcis amara (bitter almond), which grow in warm temperate regions" ; | |
skos:prefLabel "almond" . |