HY

hyperpara 1.3b v1 f16

HyperparaGGUF by ysrUpdated 2024-04-07
Download on Hugging Face
Parameters1.35B
Context16K
Layers24
Architecturellama
Smallest quant2.7 GB
Quick answer

hyperpara 1.3b v1 f16 needs about 4.8 GB of memory at F16 (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU.

hyperpara 1.3b v1 f16 is a 1.35B-parameter Hyperpara model in GGUF format, quantized by ysr. Its trained context length is 16K tokens. The repository has 1 quant file, from 2.7 GB (F16) to 2.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F162.7 GB 4.8 GB
Fits Get file →

What GPU do you need for hyperpara 1.3b v1 f16?

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: the best quant that fits is F16 (2.7 GB file, about 4.8 GB in use).

Which hyperpara 1.3b v1 f16 quant should you choose?

F16 (2.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.35B
Layers24
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byysr
FamilyHyperpara
Downloads (HF)16
Last updated2024-04-07

Frequently asked questions about hyperpara 1.3b v1 f16

How much VRAM does hyperpara 1.3b v1 f16 need?

About 4.8 GB at F16 with an 8K context window. That is the 2.7 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 hyperpara 1.3b v1 f16 on an 8 GB GPU?

Yes, with F16: the 2.7 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of hyperpara 1.3b v1 f16 GGUF?

It depends on the quant: F16 is 2.7 GB.

What context length does hyperpara 1.3b v1 f16 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download hyperpara 1.3b v1 f16 GGUF?

The files are on Hugging Face in the ysr/hyperpara-1.3b-v1-f16-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 ysr

All by ysr →

More Hyperpara models

All Hyperpara →

Other tiny models

All tiny models →