YI

Faro-Yi-9B-DPO

YiGGUF by vikarti-anatraUpdated 2024-05-25
Download on Hugging Face
Parameters8.83B
Context32K
Layers48
Architecturellama
Smallest quant4.7 GB
Quick answer

Faro-Yi-9B-DPO needs about 6.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.7 GB (Q3_K_L) to 35.3 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Faro-Yi-9B-DPO is a 8.83B-parameter Yi model in GGUF format, quantized by vikarti-anatra. Its trained context length is 32K tokens. The repository has 6 quant files, from 4.7 GB (Q3_K_L) to 35.3 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L4.7 GB 6.0 GB
Fits Get file →
Q4_K_M5.3 GB 6.6 GB
Fits Get file →
Q5_K_M6.3 GB 7.6 GB
Tight Get file →
Q6_K7.2 GB 8.6 GB
Too big Get file →
F1617.7 GB 19.0 GB
Too big Get file →
F3235.3 GB 36.6 GB
Too big Get file →

What GPU do you need for Faro-Yi-9B-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: the best quant that fits is Q3_K_L (4.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.2 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (7.2 GB file, about 8.6 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.7 GB file, about 19.0 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (17.7 GB file, about 19.0 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (35.3 GB file, about 36.6 GB in use).

Which Faro-Yi-9B-DPO quant should you choose?

Q4_K_M is the usual starting point for Faro-Yi-9B-DPO: it balances file size and quality well. Here it is a 5.3 GB file.

If memory is tight, the smallest file is Q3_K_L at 4.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.83B
Layers48
Trained context32,768 tokens
KV cache (fp16)96 KB per token

Source

Quantized byvikarti-anatra
FamilyYi
Licensemit
Downloads (HF)42
Last updated2024-05-25

Frequently asked questions about Faro-Yi-9B-DPO

How much VRAM does Faro-Yi-9B-DPO need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Faro-Yi-9B-DPO on an 8 GB GPU?

Yes, with Q5_K_M: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Faro-Yi-9B-DPO GGUF?

It depends on the quant: Q3_K_L is 4.7 GB, Q4_K_M is 5.3 GB, Q5_K_M is 6.3 GB, Q6_K is 7.2 GB, F16 is 17.7 GB, F32 is 35.3 GB.

What context length does Faro-Yi-9B-DPO support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Faro-Yi-9B-DPO GGUF?

The files are on Hugging Face in the vikarti-anatra/Faro-Yi-9B-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 Faro-Yi-9B-DPO use?

Hugging Face lists the license as mit. 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 Yi models

All Yi →

Other small models

All small models →