CO

completion-only

CompletionGGUF by krassermUpdated 2024-06-24
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant7.7 GB
Quick answer

completion-only needs about 9.3 GB of memory at Q8_0 (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

completion-only is a 7.25B-parameter Completion model in GGUF format, quantized by krasserm. Its trained context length is 32K tokens. The repository has 1 quant file, from 7.7 GB (Q8_0) to 7.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_07.7 GB 9.3 GB
Too big Get file →

What GPU do you need for completion-only?

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 (7.7 GB file, about 9.3 GB in use).

Which completion-only quant should you choose?

Q8_0 (7.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bykrasserm
Licenseapache-2.0
Downloads (HF)22
Last updated2024-06-24

Frequently asked questions about completion-only

How much VRAM does completion-only need?

About 9.3 GB at Q8_0 with an 8K context window. That is the 7.7 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 completion-only on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of completion-only GGUF?

It depends on the quant: Q8_0 is 7.7 GB.

What context length does completion-only support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download completion-only GGUF?

The files are on Hugging Face in the krasserm/gba-planner-7B-completion-only-v0.2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does completion-only use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from krasserm

All by krasserm →

More Completion models

All Completion →

Other small models

All small models →