# For academic research

GaMS-9B-Instruct is a Slovenian large language model developed based on Google Gemma 2 series, supporting Slovenian, English, and some South Slavic languages.

This is the quantized version of the c4ai-command-r7b-12-2024-abliterated model, quantized using llama.cpp, supporting multiple quantization types and suitable for various hardware environments.

This is a German Tinyllama 1B language model trained from scratch using the Tinyllama code framework and RedPajama V2 German corpus.

A 100-billion parameter model trained by Preferred Elements on open-source English-Japanese bilingual datasets, offering both commercial and non-commercial licenses

Moirai-1.1-R is a time series forecasting foundation model launched by Salesforce, with significant performance improvements for low-frequency data prediction.

A major upgrade of the Moirai-1.0-R model, demonstrating significant improvements across 40 datasets from the Monash repository, with special optimizations for low-frequency data scenarios.

Latxa is a large Basque language model based on the LLaMA-2 architecture, specifically designed for low-resource languages, trained on a 4.2 billion token Basque corpus

Cutting-edge language model specifically designed for Hebrew, a BERT-based sentiment analysis model

Japanese-enhanced large language model optimized based on the Llama 2 series, with improved instruction-following capabilities through supervised fine-tuning

LLaMA-VID is an open-source multimodal chatbot fine-tuned from LLaMA/Vicuna, supporting hours-long video processing through extended context tokens.

A 7B-parameter large language model released by Salesforce AI Research, supporting 8K long sequence input, open-sourced under Apache-2.0 license

Alpaca-7B is a large language model fine-tuned by Stanford University based on Meta's LLaMA-7B model, achieving better dialogue and task execution capabilities through instruction tuning.

Vicuna is an open-source chatbot fine-tuned from LLaMA using user-shared dialogue data, suitable for academic research.

A Russian BERT model jointly trained by Sber AI team and MLSA Lab at Moscow State University's AI Institute, specializing in scientific text processing

Provides Traditional Chinese transformers models and natural language processing tools

A Vietnamese-English bidirectional neural machine translation model developed by VinAI, utilizing advanced technology for high-quality text translation.

This model provides POS tagging functionality for ancient Chinese, with training data covering four historical periods of Chinese language development.

Provides Traditional Chinese transformers models and NLP tools including word segmentation, POS tagging, and named entity recognition.

This is a model specifically designed for Icelandic reading comprehension Q&A, as part of a master's thesis research.

Provides Traditional Chinese transformers models and natural language processing tools

Traditional Chinese natural language processing model developed by Academia Sinica's CKIP team, supporting tasks like word segmentation and part-of-speech tagging

Provides Traditional Chinese transformers models and natural language processing tools

MixQG is a question generation model pre-trained on mixed-answer-type QA datasets, capable of generating relevant questions based on given context and answers.