全站搜索
AI 模型 84757
- Qwen3.8-27B-Palimpsest-GGUF↗
xero0000
- sage-fredt5-distilled-95m↗
ai-forever
The model corrects spelling and punctuation errors and typos by bringing all the words in the text to the norm of the Russian language. Corrector is a distilled version of the original model that had been trained based on the FRED-T5-1.7B architecture. An extensive dataset with “artificial” errors was taken as a training corpus: the corpus was assembled on the basis of the Russian-language Wikipedia and transcripts of Russian-language videos, then typos and spelling errors were automatically introduced into it using the library SAGE. Below are automatic metrics for determining the correctness of the spell checkers. We compare our solution with both open automatic spell checkers and the ChatGPT family of models on all four available datasets: - **RUSpellRU**: texts collected from (LiveJournal), with manually corrected typos and errors; - **MultidomainGold**: examples from 7 text sources, including the open web, news, social media, reviews, subtitles, policy documents and literary works; - **MedSpellChecker**: texts with errors from medical anamnesis; - **GitHubTypoCorpusRu**: spelling errors and typos in commits from GitHub; **RUSpellRU** | Model | Pr. (spell) | Rec. (spell) | F1 (spell) | Pr. (punc) | Rec. (punc) | F1 (punc) | Pr. (case) | Rec. (case) | F1 (case) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | sage-fredt5-distilled-95m | 83.5 | 74.8 | 78.9 | 86.8 | 80.6 | 83.6 | 94.4 | 92.5 | 93.5 | | sage-ai-service | 90.3 | 86.3 | 88.2 | 90.3 | 86.6 | 88.4 | 95.2 | 95.9 | 95.6 | | gpt-3.5-turbo | 33.6 | 58.5 | 42.7 | 85.9 | 64.6 | 73.7 | 84.9 | 73.9 | 79.0 | | gpt-4 | 54.9 | 76.7 | 64.0 | 84.0 | 82.3 | 83.2 | 91.5 | 90.2 | 90.9 |
- Qwen3-ASR-CoreML↗
aufklarer
- Burnt-Toast_olmo-marvin-full-merged-GGUF↗
bartowski
- sup-simcse-ja-base↗
cl-nagoya
- communicative-baby-rfolmo_score↗
CLAUSE-Bielefeld
- qnli-distilroberta-base↗
cross-encoder
Given a question and paragraph, can the question be answered by the paragraph? The models have been trained on the GLUE QNLI dataset, which transformed the SQuAD dataset into an NLI task. For performance results of this model, see [SBERT.net Pre-trained Cross-Encoder][https://www.sbert.net/docs/pretrained_cross-encoders.html]. You can use the model also directly with Transformers library (without SentenceTransformers library):
- L3-Dark-Planet-8B-NEO-Imatrix-GGUF↗
DavidAU
This model has been designed to be relatively bullet proof and operates with all parameters, including temp settings from 0 to 5. It is an extraordinary compressed model, with a very low perplexity level (lower than Meta Llama3 Instruct). Note the "float32" version of this model behaves VERY differently which is why it was not uploaded first. Usually I would use the "float32" version only, however the "character range" displayed by the Bfloat16 and Float32 versions of this model dictate they have their own repos.
- DynamicMind-MoE-Instruct↗
DedeProGames
- convnextv2-large-22k-384↗
facebook