yabs.io

Yet Another Bookmarks Service

Intersect Tags

Tags

Viewing mzimmerm's Bookmarks

LLaMA 7B GPU Memory Requirement - Transformers - Hugging Face Forums

[https://discuss.huggingface.co/t/llama-7b-gpu-memory-requirement/34323/6] - 2024-03-04 10:10:38 - public:mzimmerm

ai, code, generate, llama, llm, model, newspeak, train - 8 | id:1489782 -

With the optimizers of bitsandbytes (like 8 bit AdamW), you would need 2 bytes per parameter, or 14 GB of GPU memory.

codellama (Code Llama) - Huggingface model for generating programs. Maybe can be used for Newspeak?

[https://huggingface.co/codellama] - 2024-03-03 08:48:06 - public:mzimmerm

ai, code, generate, huggingface, language, llama, model, newspeak, program - 9 | id:1489750 -

With marked bookmarks

Mark all

| (+) | |

Viewing 1 - 2, 2 links out of 2 links, page: 1

Follow Tags

llama - Please Log In To follow this tag

Export:

JSON XML RSS