pythia deduped needs about 0.9 GB of memory at F16 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB (F16) to 2.0 GB (F16).
pythia deduped is a 162M-parameter Pythia model in GGUF format, quantized by klosax. Its trained context length is 2K tokens. The repository has 4 quant files, from 0.1 GB (F16) to 2.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.3 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.6 GB | Fits | Get file → |
What GPU do you need for pythia deduped?
These figures add the file size, an fp16 KV cache at an 8K context window 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 F16 (2.0 GB file, about 2.8 GB in use).
Which pythia deduped quant should you choose?
F16 (0.3 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.
If memory is tight, the smallest file is F16 at 0.1 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about pythia deduped
How much VRAM does pythia deduped need?
About 0.9 GB at F16 with an 8K context window. That is the 0.3 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 pythia deduped on an 8 GB GPU?
Yes, with F16: the 2.0 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of pythia deduped GGUF?
It depends on the quant: F16 is 0.1 GB, F16 is 0.3 GB, F16 is 0.8 GB, F16 is 2.0 GB.
What context length does pythia deduped support?
The GGUF header lists a trained context length of 2,048 tokens (2K).
Where can I download pythia deduped GGUF?
The files are on Hugging Face in the klosax/pythia-deduped-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.