CUSTOM
CLANKERS.
← Browse all models

ArliAI / Model details

QwQ-32B-ArliAI-RpR-v4

ArliAI/QwQ-32B-ArliAI-RpR-v4

fine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

Family: Unknown. No supported family evidence recorded.

About this model

ArliAI's QwQ-32B-ArliAI-RpR-v4 is a safetensors derivative of Qwen/QwQ-32B, released under Apache-2.0. The model card describes it as the third RpR release, fine-tuned on the RpR dataset built from the curated RPMax dataset, with the goal of maintaining reasoning in long multi-turn roleplay and creative writing. The creator says v4 uses more advanced filtering to reduce repetitions and impersonation and increased training sequence length to 16K; they attribute any remaining repetition or impersonation to the base QwQ training. Training details list RS-QLORA+ with 128-rank/128-alpha, one epoch, and a learning rate of 0.00001. The creator recommends simple sampler settings such as temperature 1.0, MinP 0.02, TopK 40, and high response token limits, and says repetition-penalty samplers do not work well with RpR models.

Description sources

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model
Qwen/QwQ-32B
Parameters
32.7639B
Main repository formats
safetensors
License tag
apache-2.0
Languages
en
Last updated
2025-06-25 · 21:34:52.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

  • fine-tunedsource tag: base_model:finetune:Qwen/QwQ-32B

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

  • No supported family evidence recorded.

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/arliai-qwq-32b-arliai-rpr-v4-6bd819d0c441/)

HTML

<a href="https://customclankers.com/models/arliai-qwq-32b-arliai-rpr-v4-6bd819d0c441/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Remove more refusals

  • Heretic ↗ ★ 36,365

    Removes refusal behavior from transformer models automatically. It pairs directional ablation (abliteration) with an Optuna parameter search that tries to cut refusals while keeping the model close to the original, so you don't have to pick layers by hand.

  • OBLITERATUS ↗ ★ 8,941

    A larger refusal-removal toolkit with several abliteration methods, usable locally or through a hosted Hugging Face Space. Check the telemetry setting before you run it: the README describes telemetry as opt-in, but on by default in the Spaces version.

Fine-tune it on your own data

  • Unsloth ↗ ★ 78,505

    A desktop app and Python library for running and training models locally. Its README lists LoRA, QLoRA, full fine-tuning, DPO and GRPO, plus export to formats including GGUF, on Windows, Linux, WSL and macOS.

  • LlamaFactory ↗ ★ 75,708

    Fine-tunes more than 100 language and vision-language models from a command line or a browser-based Web UI, aimed at training without writing code.

Make a smaller download (quantize)

  • llama.cpp ↗ ★ 132,209

    Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

  • MLX LM ↗ ★ 7,461

    Apple's MLX package for running and fine-tuning models on Apple silicon. It can quantize models and upload them to the Hugging Face Hub, and supports LoRA and full fine-tuning.

Merge it with another model

  • mergekit ↗ ★ 7,414

    Merges pretrained models with many merge methods. It works out-of-core, so merges can run on a CPU or with as little as 8 GB of VRAM, and it also handles LoRA extraction and mixture-of-experts merges.

Learn the techniques

  • LLM Course ↗ ★ 84,653

    A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads
109
Likes
44
Metadata checked
2026-10-24 · 16:13:40 UTC
First seen in index
2026-10-24 · 16:13:40 UTC
Source revision
ad85eec4a5114a37bf974accbdd5afc062759231

Source-card excerpt

Source model card excerpt: QwQ-32B-ArliAI-RpR-v4 Image generated using Arli AI Image Generation Different RpR Versions Small - 8B Fast - 30B-A3B OG - 32B Large - 70B RpR

From ArliAI/QwQ-32B-ArliAI-RpR-v4. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗