SO

240216 SOL 11B base zephyer template qlora adaptor fp16merged

SolGGUF by shidowakeUpdated 2024-02-21
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant7.6 GB
Quick answer

240216 SOL 11B base zephyer template qlora adaptor fp16merged needs about 9.7 GB of memory at Q5_K_M (a 7.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.6 GB (Q5_K_M) to 11.4 GB (Q8_0).

240216 SOL 11B base zephyer template qlora adaptor fp16merged is a 10.7B-parameter Sol model in GGUF format, quantized by shidowake. Its trained context length is 4K tokens. The repository has 2 quant files, from 7.6 GB (Q5_K_M) to 11.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M7.6 GB 8.9 GB
Too big Get file →
Q8_011.4 GB 12.7 GB
Too big Get file →

What GPU do you need for 240216 SOL 11B base zephyer template qlora adaptor fp16merged?

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_M (7.6 GB file, about 9.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which 240216 SOL 11B base zephyer template qlora adaptor fp16merged quant should you choose?

Q5_K_M (7.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byshidowake
FamilySol
Downloads (HF)13
Last updated2024-02-21

Frequently asked questions about 240216 SOL 11B base zephyer template qlora adaptor fp16merged

How much VRAM does 240216 SOL 11B base zephyer template qlora adaptor fp16merged need?

About 9.7 GB at Q5_K_M with an 8K context window. That is the 7.6 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 240216 SOL 11B base zephyer template qlora adaptor fp16merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of 240216 SOL 11B base zephyer template qlora adaptor fp16merged GGUF?

It depends on the quant: Q5_K_M is 7.6 GB, Q8_0 is 11.4 GB.

What context length does 240216 SOL 11B base zephyer template qlora adaptor fp16merged support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download 240216 SOL 11B base zephyer template qlora adaptor fp16merged GGUF?

The files are on Hugging Face in the shidowake/240216_SOL-11B-base-zephyer-template-qlora-adaptor-fp16merged-GGUF 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 shidowake

All by shidowake →

More Sol models

All Sol →

Other medium models

All medium models →