DO

42dot LLM SFT 1.3B

DotGGUF by rozekUpdated 2023-11-21
Download on Hugging Face
Parameters1.44B
Context4K
Layers24
Architecturellama
Smallest quant0.9 GB
Quick answer

42dot LLM SFT 1.3B needs about 3.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.9 GB (Q4_K_M) to 5.8 GB.

42dot LLM SFT 1.3B is a 1.44B-parameter Dot model in GGUF format, quantized by rozek. Its trained context length is 4K tokens. The repository has 5 quant files, from 0.9 GB (Q4_K_M) to 5.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.9 GB 2.2 GB
Fits Get file →
Q5_K_M1.0 GB 2.3 GB
Fits Get file →
Q6_K1.2 GB 2.5 GB
Fits Get file →
Q8_01.5 GB 2.8 GB
Fits Get file →
—5.8 GB 7.1 GB
Fits Get file →

What GPU do you need for 42dot LLM SFT 1.3B?

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: the best quant that fits is Q8_0 (1.5 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.5 GB file, about 3.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.8 GB file, about 7.9 GB in use).

Which 42dot LLM SFT 1.3B quant should you choose?

Q4_K_M is the usual starting point for 42dot LLM SFT 1.3B: it balances file size and quality well. Here it is a 0.9 GB file.

The Q8_0 file is 1.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.44B
Layers24
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byrozek
FamilyDot
Downloads (HF)74
Last updated2023-11-21

Frequently asked questions about 42dot LLM SFT 1.3B

How much VRAM does 42dot LLM SFT 1.3B need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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 42dot LLM SFT 1.3B on an 8 GB GPU?

Yes, with the smaller files: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 42dot LLM SFT 1.3B GGUF?

It depends on the quant: Q4_K_M is 0.9 GB, Q5_K_M is 1.0 GB, Q6_K is 1.2 GB, Q8_0 is 1.5 GB, file is 5.8 GB.

What context length does 42dot LLM SFT 1.3B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download 42dot LLM SFT 1.3B GGUF?

The files are on Hugging Face in the rozek/42dot_LLM-SFT-1.3B_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 42dot LLM SFT 1.3B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 rozek

All by rozek →

More Dot models

All Dot →

Other tiny models

All tiny models →