Vocabtrimmer
Rank:Average Model Cost: $0.0000
Number of Runs: 155
Models by this creator
mt5-small-trimmed-ru-30000-ruquad-qa
mt5-small-trimmed-ru-30000-ruquad-qa
Platform did not provide a description for this model.
$-/run
23
Huggingface
mt5-small-trimmed-it-90000-itquad-qa
mt5-small-trimmed-it-90000-itquad-qa
Model Card of vocabtrimmer/mt5-small-trimmed-it-90000-itquad-qa This model is fine-tuned version of vocabtrimmer/mt5-small-trimmed-it-90000 for question answering task on the lmqg/qg_itquad (dataset_name: default) via lmqg. Overview Language model: vocabtrimmer/mt5-small-trimmed-it-90000 Language: it Training data: lmqg/qg_itquad (default) Online Demo: https://autoqg.net/ Repository: https://github.com/asahi417/lm-question-generation Paper: https://arxiv.org/abs/2210.03992 Usage With lmqg With transformers Evaluation Metric (Question Answering): raw metric file Training hyperparameters The following hyperparameters were used during fine-tuning: dataset_path: lmqg/qg_itquad dataset_name: default input_types: ['paragraph_question'] output_types: ['answer'] prefix_types: None model: vocabtrimmer/mt5-small-trimmed-it-90000 max_length: 512 max_length_output: 32 epoch: 14 batch: 32 lr: 0.0005 fp16: False random_seed: 1 gradient_accumulation_steps: 2 label_smoothing: 0.15 The full configuration can be found at fine-tuning config file. Citation
$-/run
18
Huggingface
mbart-large-cc25-trimmed-ko-koquad-qa
mbart-large-cc25-trimmed-ko-koquad-qa
Platform did not provide a description for this model.
$-/run
17
Huggingface
xlm-v-base-tweet-sentiment-fr-trimmed-fr
xlm-v-base-tweet-sentiment-fr-trimmed-fr
Vocabulary Trimmed cardiffnlp/xlm-v-base-tweet-sentiment-fr: vocabtrimmer/xlm-v-base-tweet-sentiment-fr-trimmed-fr This model is a trimmed version of cardiffnlp/xlm-v-base-tweet-sentiment-fr by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size. Following table shows a summary of the trimming process. Following table shows the parameter used to trim vocabulary.
$-/run
17
Huggingface
mt5-small-trimmed-it-30000-itquad-qg
mt5-small-trimmed-it-30000-itquad-qg
Platform did not provide a description for this model.
$-/run
14
Huggingface
mt5-small-trimmed-ru-120000-ruquad-qg
mt5-small-trimmed-ru-120000-ruquad-qg
Platform did not provide a description for this model.
$-/run
14
Huggingface
xlm-roberta-base-trimmed-en-30000-xnli-en
xlm-roberta-base-trimmed-en-30000-xnli-en
Platform did not provide a description for this model.
$-/run
13
Huggingface
xlm-v-base-trimmed-fr-xnli-fr
xlm-v-base-trimmed-fr-xnli-fr
Platform did not provide a description for this model.
$-/run
13
Huggingface
xlm-roberta-base-tweet-sentiment-fr-trimmed-fr-15000
xlm-roberta-base-tweet-sentiment-fr-trimmed-fr-15000
Platform did not provide a description for this model.
$-/run
13
Huggingface
xlm-v-base-trimmed-es-tweet-sentiment-es
xlm-v-base-trimmed-es-tweet-sentiment-es
vocabtrimmer/xlm-v-base-trimmed-es-tweet-sentiment-es This model is a fine-tuned version of /home/c.c2042013/lm-vocab-trimmer/ckpts/xlm-v-base-trimmed-es on the cardiffnlp/tweet_sentiment_multilingual (spanish). Following metrics are computed on the test split of cardiffnlp/tweet_sentiment_multilingual(spanish). Check the result file here.
$-/run
13
Huggingface