SO

solarized 13B dpo

SolarGGUF by vicgalleUpdated 2024-01-20
Download on Hugging Face
Parameters12.5B
Context4K
Layers56
Architecturellama
Smallest quant7.5 GB
Quick answer

solarized 13B dpo needs about 11.2 GB of memory at Q5_K (a 8.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.5 GB (Q4_K) to 10.2 GB (Q6_K).

solarized 13B dpo is a 12.5B-parameter Solar model in GGUF format, quantized by vicgalle. Its trained context length is 4K tokens. The repository has 3 quant files, from 7.5 GB (Q4_K) to 10.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K7.5 GB 8.9 GB
Too big Get file →
Q5_K8.8 GB 10.3 GB
Too big Get file →
Q6_K10.2 GB 11.7 GB
Too big Get file →

What GPU do you need for solarized 13B dpo?

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 Q5_K (8.8 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.2 GB file, about 12.6 GB in use).

Which solarized 13B dpo quant should you choose?

Q5_K (8.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_K at 7.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.5B
Layers56
Trained context4,096 tokens
KV cache (fp16)224 KB per token

Source

Quantized byvicgalle
FamilySolar
Licenseapache-2.0
Downloads (HF)22
Last updated2024-01-20

Frequently asked questions about solarized 13B dpo

How much VRAM does solarized 13B dpo need?

About 11.2 GB at Q5_K with an 8K context window. That is the 8.8 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 solarized 13B dpo on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of solarized 13B dpo GGUF?

It depends on the quant: Q4_K is 7.5 GB, Q5_K is 8.8 GB, Q6_K is 10.2 GB.

What context length does solarized 13B dpo support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.9 GB at 8K and 0.9 GB at 4K.

Where can I download solarized 13B dpo GGUF?

The files are on Hugging Face in the vicgalle/solarized-13B-dpo-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 solarized 13B dpo 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.

Other GGUFs of SOLAR-13B-Instruct-v1.0

Similar models

Browse all →

More from vicgalle

All by vicgalle →

More Solar models

All Solar →

Other medium models

All medium models →