Spaces:
Sleeping
Sleeping
title: VRAM Estimator | |
emoji: 🧮 | |
colorFrom: yellow | |
colorTo: blue | |
sdk: gradio | |
sdk_version: 4.39.0 | |
app_file: app.py | |
pinned: false | |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |
TODO: | |
- include vocab size as manual parameter | |
- include finetuning techniques (LoRA/QLoRA/LoftQ) | |
- include inference (KV cache memory) | |
- include number of experts for Mixture of Experts (MoE) models | |
- include DeepSpeed communication memory overhead (`allgather_bucket_size`) |