Dolphin-Mistral-24B-Venice-Edition is a large open-weight language model derived from Mistral. It features enhanced instruction-following capabilities and a specialized chat template. It can be used via Hugging Face transformers for text generation, chat, and other generative tasks.
Dolphin Mistral 24B Venice Edition is a Foundation models & chat project. It focuses on running high-quality instruction-tuned large language models locally or on custom infrastructure. It is built as an open-source project for developers. Dolphin Mistral 24B Venice Edition is open source under the Apache-2.0 license. It runs on the web, the command line, and API.
Behind Dolphin Mistral 24B Venice Edition is dphn, and it first shipped in 2023. Development happens publicly on GitHub with 86.8k stars and 3k commits in the last 90 days.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do