CoolFace
Modelpublic

blockblockblock/pagestorm-research-preview-14b-full-book-exl3-4.0bpw

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes63downloads
Model Card

<div align="center">

pagestorm · research · preview · 14b · full · book

<sub><code>EXL3</code> &nbsp;·&nbsp; <b>4.0&nbsp;bpw</b> &nbsp;·&nbsp; 8.2&nbsp;GB &nbsp;·&nbsp; Dense &nbsp;·&nbsp; 40 layers</sub>

<br/>

![format](https://github.com/turboderp-org/exllamav3) ![bpw](#quants) ![size](#quants) ![arch](https://huggingface.co/Pageshift-Entertainment/pagestorm-research-preview-14b-full-book)

![base model](https://huggingface.co/Pageshift-Entertainment/pagestorm-research-preview-14b-full-book) ![quantized by](https://huggingface.co/blockblockblock) ![collection](https://huggingface.co/collections/blockblockblock/pagestorm-research-preview-14b-full-book-exl3-6a4436531823ca866b3b6121)

</div>


[!NOTE] An ExLlamaV3 build of `Pageshift-Entertainment/pagestorm-research-preview-14b-full-book` at 4.0 bits per weight. See Quants for sibling repos at other bit&#8209;widths or browse the collection.

Quants

<div align="center">

BPW &nbsp;&nbsp; Head bits &nbsp;&nbsp; Calibration rows &nbsp;&nbsp; Size &nbsp;&nbsp; Status
4.082508.2&nbsp;GB<kbd>this repo</kbd>
6.0825011.2&nbsp;GBlink

</div>

Inference

<table> <thead> <tr> <th align="left" width="32%">Loader</th> <th align="left">Use it for</th> </tr> </thead> <tbody> <tr> <td><a href="https://github.com/theroyallab/tabbyAPI"><b>TabbyAPI</b></a></td> <td>OpenAI&#8209;compatible HTTP server. Drop&#8209;in for OpenAI clients.</td> </tr> <tr> <td><a href="https://github.com/oobabooga/text-generation-webui"><b>text&#8209;generation&#8209;webui</b></a></td> <td>Local chat UI. Pick the <i>ExLlamaV3</i> loader from the model dropdown.</td> </tr> <tr> <td><a href="https://github.com/turboderp-org/exllamav3"><b>ExLlamaV3</b></a></td> <td>Direct Python API for embedding the model in your own code or pipeline.</td> </tr> </tbody> </table>

Download

bash
pip install -U huggingface_hub

hf download \
  blockblockblock/pagestorm-research-preview-14b-full-book-exl3-4.0bpw \
  --local-dir ./pagestorm-research-preview-14b-full-book-exl3-4.0bpw

<details> <summary><b>Quantization recipe</b> &nbsp;<sub>(advanced, embedded in <code>quantization_config.json</code>)</sub></summary>

<br/>

SettingValue
FormatEXL3
Bits per weight4.0
Head bits8
Calibration rows250
CodebookMCG
Out&#8209;scalesalways
Parallel modeenabled

Loaded automatically by every ExLlamaV3 loader; reproduced here for searchability.

</details>

License &amp; use

[!IMPORTANT] Use and license follow the [base model](https://huggingface.co/Pageshift-Entertainment/pagestorm-research-preview-14b-full-book). Quantization adds no additional restrictions. Refer to the upstream repository for terms, citation, and safety documentation.

<div align="center"> <sub><i>Quantized with <a href="https://github.com/Honkware/blockquant"><b>BlockQuant</b></a> &nbsp;·&nbsp; convention&nbsp;<code>{org}/{model}-exl3-{bpw}bpw</code></i></sub> </div>