A 70 billion parameter fine-tune of Meta's Llama 3 model optimized for conversational and instruction-following tasks. It uses a specific chat template and can be deployed locally with tools like Docker or via inference providers. The model is fully open-weight for self-hosting and customization.
Dolphin 2.9.1 Llama 3 70b sits in PulseGate's Foundation models & chat category. It focuses on running a capable open-source conversational LLM locally or via hosted inference. Dolphin 2.9.1 Llama 3 70b is an open-source project aimed at developers. Dolphin 2.9.1 Llama 3 70b is open source under the Apache-2.0 license. It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by dphn, and it first shipped in 2024. The project is developed in the open on GitHub with 240 stars. Among its 3 catalogued features are Chat Template, Instruction Tuning, and 70B Parameters. It exposes integrations via a public API.
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