A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes Aug 17, 2022 • 61
view post Post 2386 Reply Falcon Mamba now available now in llama.cpp !Check out GGUF files uploaded here: tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a
view post Post 3239 Reply FalconMamba 7B - a new model from TII (Technology Innovation Institute) is out !- Blogpost: https://huggingface.co/blog/falconmamba- Link to collection: tiiuae/falconmamba-7b-66b9a580324dd1598b0f6d4a- Link to playground: tiiuae/falcon-mamba-playground
Sharded checkpoints useful sharded checkpoints for users to run inference / fine-tuning on a Google colab without having to deal with CPU OOM issues. ybelkada/falcon-7b-sharded-bf16 Text Generation • Updated Apr 10 • 4.57k • 20 ybelkada/blip2-opt-2.7b-fp16-sharded Visual Question Answering • Updated Apr 12, 2023 • 4.79k • 3 ybelkada/flan-t5-xl-sharded-bf16 Text2Text Generation • Updated Feb 16, 2023 • 1.05k • 12 ybelkada/mpt-7b-bf16-sharded Text Generation • Updated Jul 21, 2023 • 47