LL

ELYZA japanese Llama 2 13b fast instruct

LlamaGGUF by schronekoUpdated 2024-01-25
Download on Hugging Face
Parameters13.1B
Context4K
Layers40
Architecturellama
Smallest quant8.0 GB
Quick answer

ELYZA japanese Llama 2 13b fast instruct needs about 15.2 GB of memory at its main file (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU.

ELYZA japanese Llama 2 13b fast instruct is a 13.1B-parameter Llama model in GGUF format, quantized by schroneko. Its trained context length is 4K tokens. The repository has 1 quant file, from 8.0 GB to 8.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.0 GB 11.8 GB
Too big Get file →

What GPU do you need for ELYZA japanese Llama 2 13b fast instruct?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (8.0 GB file, about 15.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.1B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byschroneko
FamilyLlama
Licensellama2
Downloads (HF)111
Last updated2024-01-25

Frequently asked questions about ELYZA japanese Llama 2 13b fast instruct

How much VRAM does ELYZA japanese Llama 2 13b fast instruct need?

About 15.2 GB at its main file with an 8K context window. That is the 8.0 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 ELYZA japanese Llama 2 13b fast instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ELYZA japanese Llama 2 13b fast instruct GGUF?

It depends on the quant: file is 8.0 GB.

What context length does ELYZA japanese Llama 2 13b fast instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download ELYZA japanese Llama 2 13b fast instruct GGUF?

The files are on Hugging Face in the schroneko/ELYZA-japanese-Llama-2-13b-fast-instruct-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 ELYZA japanese Llama 2 13b fast instruct use?

Hugging Face lists the license as llama2. 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 Llama models

All Llama →

Other medium models

All medium models →