Catalog

481 - 492 of 593
Unsigned
1K+
1
qwen2-0.5b

By

Latest ModelKit

Model
Datasets
Codebases
2
Docs
Prompts/Skills
Unsigned
1K+
1
javis-sms-detection

By

Latest ModelKit

Model
Datasets
1
Codebase
1
Doc
Prompts/Skills
Unsigned
1K+
1
sms-spam-javis

By

Latest ModelKit

Model
Datasets
1
Codebase
1
Doc
Prompts/Skills
Unsigned
1K+
1
omniparser-v2.0

By

Latest ModelKit

Model
Datasets
2
Codebases
1
Doc
Prompts/Skills
Unsigned
1K+
1
bert-tiny-finetuned-sms-spam-detection

By

Latest ModelKit

Model
Datasets
1
Codebase
1
Doc
Prompts/Skills
Unsigned
238
3
testing

By

Latest ModelKit

Model
Datasets
Codebases
Docs
Prompts/Skills
Unsigned
605
1
gpt2-distilled-lora-alpaca

By

Latest ModelKit

Model
Datasets
Codebases
1
Doc
Prompts/Skills
Unsigned
0
0
microsoft-phi-2

By

Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.

Latest ModelKit

Model
Datasets
Codebases
Docs
Prompts/Skills
Unsigned
775
1
llama3-githubactions

By

Latest ModelKit

Model
Datasets
3
Codebases
Docs
Prompts/Skills
Unsigned
0
0
microsoft_phi-2

By

Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.

Latest ModelKit

Model
Datasets
Codebases
Docs
Prompts/Skills
Unsigned
0
0
microsoft_phi-4

By

phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning. phi-4 underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures

Latest ModelKit

Model
Datasets
Codebases
Docs
Prompts/Skills
Unsigned
0
0
fraud-detection-model

By

Fraud detection model using sklearn

Latest ModelKit

Model
Datasets
Codebases
Docs
Prompts/Skills