PY

Pythia 1.4b Deduped

PythiaGGUF by mradermacherUpdated 2024-09-08
Download on Hugging Face
Parameters1.41B
Context2K
Layers24
Architecturegptneox
Smallest quant0.6 GB
Quick answer

Pythia 1.4b Deduped 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 15 quants, from 0.6 GB (Q2_K) to 2.8 GB (F16).

Pythia 1.4b Deduped – 1.41B‑parameter GPT-NeoX model in GGUF format

Pythia 1.4b Deduped is a 1.41B‑parameter transformer trained on a deduplicated Pile dataset. It supports 2048‑token context and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Interpretability research
  • Baseline performance for 1.4B models
  • Open‑source community use

Limits

  • No vision support
  • Context limited to 2048 tokens
  • Requires GPU with at least 3 GB VRAM for Q4_K_M

Best for

  • Running on mid‑range GPUs
  • Fine‑tuning small datasets
  • Educational demonstrations

Who it’s for. Developers and researchers who need a lightweight, open‑source 1.4B language model for experimentation. The model is suitable for those who prefer a deduplicated dataset and want to avoid large GPU memory footprints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.6 GB 1.5 GB
Fits Get file →
IQ3_XS0.6 GB 1.5 GB
Fits Get file →
IQ3_S0.7 GB 1.6 GB
Fits Get file →
Q3_K_S0.7 GB 1.6 GB
Fits Get file →
IQ3_M0.7 GB 1.6 GB
Fits Get file →
Q3_K_M0.8 GB 1.7 GB
Fits Get file →
IQ4_XS0.8 GB 1.7 GB
Fits Get file →
Q3_K_L0.8 GB 1.7 GB
Fits Get file →
Q4_K_S0.8 GB 1.7 GB
Fits Get file →
Q4_K_M0.9 GB 1.8 GB
Fits Get file →
Q5_K_S1.0 GB 1.9 GB
Fits Get file →
Q5_K_M1.1 GB 2.0 GB
Fits Get file →
Q6_K1.2 GB 2.1 GB
Fits Get file →
Q8_01.5 GB 2.4 GB
Fits Get file →
F162.8 GB 3.7 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.92 GB) or Q5_K_M (1.06 GB) are recommended. If memory is tighter, Q3_K_M (0.76 GB) or IQ3_S (0.65 GB) provide a balance between size and performance. For maximum quality, use Q8_0 (1.51 GB).

What GPU do you need for Pythia 1.4b Deduped?

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 F16 (2.8 GB file, about 4.9 GB in use).

Which Pythia 1.4b Deduped quant should you choose?

Q4_K_M is the usual starting point for Pythia 1.4b Deduped: it balances file size and quality well. Here it is a 0.9 GB file.

The Q8_0 file is 1.5 GB, about 1.6 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.

If memory is tight, the smallest file is Q2_K at 0.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegptneox
Parameters1.41B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyPythia
Licenseapache-2.0
Downloads (HF)364
Last updated2024-09-08

Frequently asked questions about Pythia 1.4b Deduped

How much VRAM does Pythia 1.4b Deduped 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 Pythia 1.4b Deduped on an 8 GB GPU?

Yes, with F16: the 2.8 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pythia 1.4b Deduped GGUF?

It depends on the quant: Q2_K is 0.6 GB, IQ3_XS is 0.6 GB, IQ3_S is 0.7 GB, Q3_K_S is 0.7 GB, IQ3_M is 0.7 GB, Q3_K_M is 0.8 GB and 9 more.

What context length does Pythia 1.4b Deduped support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download Pythia 1.4b Deduped GGUF?

The files are on Hugging Face in the mradermacher/pythia-1.4b-deduped-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 Pythia 1.4b Deduped 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.

Can I run Pythia 1.4b Deduped on 8 GB VRAM?

Yes, quantizations such as Q4_K_M (0.92 GB) or Q5_K_M (1.06 GB) fit within 8 GB VRAM, with estimated memory usage around 3 GB at 8k context.

What context length does the model support?

The model is trained with a context length of 2048 tokens.

Is the model licensed for commercial use?

It is released under the Apache‑2.0 license, which permits commercial use.

Other GGUFs of pythia-1.4b-deduped

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Pythia models

All Pythia →

Other tiny models

All tiny models →