CUSTOM
CLANKERS.
← Browse all models

Goekdeniz-Guelmez / Model details

Qwen3.5-0.8B-Base-RL

Goekdeniz-Guelmez/Qwen3.5-0.8B-Base-RL

fine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

Summarize and ask questions with AI

About this model

Goekdeniz-Guelmez's derivative of Qwen/Qwen3.5-0.8B, distributed as safetensors weights under an Apache-2.0 license. The creator states this is not GRPO trained; it contains the base model weights with a custom chat template intended for later GRPO use. The template defines a JOSIE-3 persona and a system prompt asking for explicit raw reasoning, with output divided into thinking and answer tags. The model card says a custom version with more reasoning depths and a custom system prompt is used for GRPO. No independent evaluation of behavior or capabilities is provided here.

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/Qwen3.5-0.8B
Parameters
873.439M
Main repository formats
safetensors
License tag
apache-2.0
Languages
Unknown
Last updated
2026-10-06 · 11:41:17.000 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/Qwen3.5-0.8B

Family evidence

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

  • Qwen: Base model: Qwen/Qwen3.5-0.8B

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/goekdeniz-guelmez-qwen3-5-0-8b-base-rl/)

HTML

<a href="https://customclankers.com/models/goekdeniz-guelmez-qwen3-5-0-8b-base-rl/">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 ↗ ★ 37,281

    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 ↗ ★ 9,054

    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 ↗ ★ 78,860

    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 ↗ ★ 75,803

    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 ↗ ★ 132,963

    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 ↗ ★ 7,514

    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 ↗ ★ 7,426

    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 ↗ ★ 84,813

    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
16
Likes
0
Metadata checked
2026-10-31 · 16:11:41 UTC
First seen in index
2026-10-31 · 16:11:41 UTC
Source revision
c5555e0678d577a4a59f5356966d442d27639f2f

Source-card excerpt

Source model card excerpt: Goekdeniz-Guelmez/Qwen3.5-0.8B-Base-RL NOT GRPO trained!!!!! THESE ARE JUST THE BASE MODEL WEIGHTS WITH A CUSTOM CHAT TEMPLATE Used for GRPO has a custom version with

From Goekdeniz-Guelmez/Qwen3.5-0.8B-Base-RL. 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 ↗