💫 Community Model Llama 3.1 8B Instruct by Meta 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord . Model creator: meta llama Original model : Meta Llama 3.1 8B Instruct GGUF quantization: provided by bartowski based on llama.cpp release b3472 Important: Requires LM Studio version 0.2.29, available now here! Model Summary: Llama 3.1 is an update to the previously released family of Llama 3 models. It has improved performance across the board, especially in multilingual tasks. It is the current state of the art for open source and can be used for basically any task you throw at it. Prompt Template: Choose the 'Llama 3' preset in your LM Studio. Under the hood, the model will see a prompt that's formatted like so: Technical Details Llama 3.1 features an improved 128k context window. It has been trained on 15T tokens, including 25 million synthetically generated samples. For more details, check their blog post here Special thanks 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. 🙏 Special thanks to Kalomaze for his dataset (linked here)…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy