OR

it-5.4-fp16-orpo-v2

OrpoGGUF by dkramorovUpdated 2024-09-10
Download on Hugging Face
Parameters7.63B
Context32K
Layers32
Architecturellama
Smallest quant5.4 GB
Quick answer

it-5.4-fp16-orpo-v2 needs about 7.0 GB of memory at Q5_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

it-5.4-fp16-orpo-v2 is a 7.63B-parameter Orpo model in GGUF format, quantized by dkramorov. Its trained context length is 32K tokens. The repository has 1 quant file, from 5.4 GB (Q5_K_M) to 5.4 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.4 GB 7.0 GB
Fits Get file →

What GPU do you need for it-5.4-fp16-orpo-v2?

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: the best quant that fits is Q5_K_M (5.4 GB file, about 7.0 GB in use).

Which it-5.4-fp16-orpo-v2 quant should you choose?

Q5_K_M (5.4 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
Parameters7.63B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydkramorov
FamilyOrpo
Downloads (HF)3
Last updated2024-09-10

Frequently asked questions about it-5.4-fp16-orpo-v2

How much VRAM does it-5.4-fp16-orpo-v2 need?

About 7.0 GB at Q5_K_M with an 8K context window. That is the 5.4 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 it-5.4-fp16-orpo-v2 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.4 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of it-5.4-fp16-orpo-v2 GGUF?

It depends on the quant: Q5_K_M is 5.4 GB.

What context length does it-5.4-fp16-orpo-v2 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 it-5.4-fp16-orpo-v2 GGUF?

The files are on Hugging Face in the dkramorov/it-5.4-fp16-orpo-v2-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 Orpo models

All Orpo →

Other small models

All small models →