RE

repo

RepoGGUF by victunesUpdated 2024-04-21
Download on Hugging Face
Parameters10.7B
Context8K
Layers32
Architecturellama
Smallest quant8.5 GB
Quick answer

repo needs about 13.0 GB of memory at Q8_0 (a 11.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 8 quants, from 8.5 GB (Q8_0) to 21.5 GB (F16).

repo is a 10.7B-parameter Repo model in GGUF format, quantized by victunes. Its trained context length is 8K tokens. The repository has 8 quant files, from 8.5 GB (Q8_0) to 21.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.5 GB 10.1 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
Q8_011.4 GB 13.0 GB
Too big Get file →
Q8_011.4 GB 13.0 GB
Too big Get file →
Q8_011.4 GB 13.0 GB
Too big Get file →
—11.4 GB 13.0 GB
Too big Get file →
F1621.5 GB 23.0 GB
Too big Get file →
F1621.5 GB 23.0 GB
Too big Get file →

What GPU do you need for repo?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.0 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (21.5 GB file, about 23.0 GB in use).

Which repo quant should you choose?

Q8_0 (11.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q8_0 at 8.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byvictunes
FamilyRepo
Repositoryvictunes/repo
Downloads (HF)76
Last updated2024-04-21

Frequently asked questions about repo

How much VRAM does repo need?

About 13.0 GB at Q8_0 with an 8K context window. That is the 11.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run repo on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of repo GGUF?

It depends on the quant: Q8_0 is 8.5 GB, Q8_0 is 8.5 GB, Q8_0 is 11.4 GB, Q8_0 is 11.4 GB, Q8_0 is 11.4 GB, file is 11.4 GB and 2 more.

What context length does repo support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download repo GGUF?

The files are on Hugging Face in the victunes/repo repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from victunes

All by victunes →

More Repo models

All Repo →

Other medium models

All medium models →