license: apache-2.0 datasets:
- TeichAI/claude-4.5-opus-high-reasoning-250x language:
- en library_name: transformers tags:
- finetune
- unsloth
- abliterated
- uncensored
- specialized post tuning
- claude-4.5-opus
- reasoning
- thinking
- distill-fine-tune
- moe
- 128 experts
- 256k context
- mixture of experts base_model:
- huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated pipeline_tag: text-generation
The power of Claude 4.5 Opus High Reasoning with the MOE power (and speed) of Qwen 30B-A3B 2507 Thinking (256k context, 128 experts).
This version is both fully uncensored, and fully functional too.
Benchmarks (below) show that this version exceeds the org model in 6 out of 8 metrics and very closely matches in the other 2.
Tuning via Unsloth (on local hardware) using Linux for Windows.
Specialized tuning applied on an abliterated model post abliteration to bring both new reasoning (Claude) and repair any ablit model issues.
Compact, to the point, and powerful reasoning takes "Qwen 30B-A3B 2507 Thinking" to the next level.
Reasoning/Thinking blocks will be a lot shorter, and in many cases different from "Qwen" reasoning.
Note all math, science and other goodies are fully intact.
Model Specs:
- 256k context
- 128 experts (8 active by default)
- 3B of 30B parameters active.
- Model can be used on GPU, CPU or split at reasonable token/second speed.
BENCHMARKS:
[ xxx ] - Exceeds org model specs.
ARC-Challenge | ARC-Easy | BoolQ | Hellaswag | OpenBookQA | PIQA | Winogrande
[0.405] [0.476] [0.804] [0.656] 0.374 [0.781] [0.653]
NOTE: "Arc-C" exceeds Abliterated model, but not "normal Qwen 3 30B-A3B"
VS "Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated"
ARC-Challenge | ARC-Easy | BoolQ | Hellaswag | OpenBookQA | PIQA | Winogrande
0.387 0.436 0.628 0.616 0.400 0.763 0.639
VS "Normal Qwen3 30B-A3B"
ARC-Challenge | ARC-Easy | BoolQ | Hellaswag | OpenBookQA | PIQA | Winogrande
0.410 0.444 0.691 0.635 0.390 0.769 0.650
Using an "uncensored" (refusals removed) model VS trained "uncensored" model
Usually when you a tell a model to generate horror, swear or x-rated content this is all you have to do to get said content type.
In the case of this model, it will not refuse your request, however it needs to be "pushed" a bit / directed a bit more in SOME CASES.
Although this model will generated x-rated content too, likewise you need to tell it to use "slang" (and include the terms you want) to get it generate the content correctly as the "expected" content level too.
Without these added directive(s), the content can be "bland" by comparison to an "uncensored model" or model trained on uncensored content.
Roughly, the model tries to generate the content but the "default" setting(s) are so "tame" it needs a push to generate at expected graphic, cursing or explicit levels.
Even with minimal direction (ie, use these words to swear: x,y,z), this will be enough to push the model to generate the requested content in the ahh... expected format.
Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
OTHER OPTIONS:
-
Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
-
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here: