MO

MoMo 70B lora 1.8.6 DPO

MomoGGUF by senseableUpdated 2024-01-19
Download on Hugging Face
Parameters72.3B
Context32K
Layers80
Architecturellama
Smallest quant43.8 GB
Quick answer

MoMo 70B lora 1.8.6 DPO needs about 65.7 GB of memory at Q4_K_M (a 43.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.

MoMo 70B lora 1.8.6 DPO is a 72.3B-parameter Momo model in GGUF format, quantized by senseable. Its trained context length is 32K tokens. The repository has 1 quant file, from 43.8 GB (Q4_K_M) to 43.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M43.8 GB 65.7 GB
Too big Get file →

What GPU do you need for MoMo 70B lora 1.8.6 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: 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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which MoMo 70B lora 1.8.6 DPO quant should you choose?

Q4_K_M is the usual starting point for MoMo 70B lora 1.8.6 DPO: it balances file size and quality well. Here it is a 43.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters72.3B
Layers80
Trained context32,768 tokens
KV cache (fp16)2560 KB per token

Source

Quantized bysenseable
FamilyMomo
Licenseapache-2.0
Downloads (HF)22
Last updated2024-01-19

Frequently asked questions about MoMo 70B lora 1.8.6 DPO

How much VRAM does MoMo 70B lora 1.8.6 DPO need?

About 65.7 GB at Q4_K_M with an 8K context window. That is the 43.8 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 MoMo 70B lora 1.8.6 DPO on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 65.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MoMo 70B lora 1.8.6 DPO GGUF?

It depends on the quant: Q4_K_M is 43.8 GB.

What context length does MoMo 70B lora 1.8.6 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 21.5 GB at 8K and 85.9 GB at 32K.

Where can I download MoMo 70B lora 1.8.6 DPO GGUF?

The files are on Hugging Face in the senseable/MoMo-70B-lora-1.8.6-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 MoMo 70B lora 1.8.6 DPO use?

Hugging Face lists the license as apache-2.0. 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 from senseable

All by senseable →

More Momo models

All Momo →

Other large models

All large models →