The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.

The Mixtral-8x7B Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x7B MoE (Mixture of Experts) model.

The Mixtral-8x22B Large Language Model (LLM) is an instruct fine-tuned version of the Mixtral-8x22B MoE (Mixture of Experts) model.

The Meta-Llama-3.1-8B-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the Meta-Llama-3.1-8B model.

The Meta-Llama-3.1-70B-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the Meta-Llama-3.1-70B model.

The Phi-3-Mini-4K-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the Phi-3.5-Mini-4K model.

The Qwen2-7B-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the Qwen2-7B model.

Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web.

GTE Multilingual Base is from the GTE (General Text Embedding) family of models. Achieving state-of-the-art (SOTA) results and supporting over 70 languages.

GTE Multilingual Base is part of the GTE (General Text Embedding) family of models. It achieves state-of-the-art (SOTA) results on English text, offering the best overall performance relative to its number of parameters.