license, language, base_model, datasets, pipeline_tag, library_name, tags

license	language	base_model	datasets	pipeline_tag	library_name	tags
apache-2.0	en	DavidAU/LFM2.5-1.2B-MEGABRAIN-Thinking-Polaris-ClaudeHOPUS-Deepseek-GLM	TeichAI/kimi-k2-thinking-1000x	text-generation	transformers	unsloth finetune All use cases bfloat16 creative creative writing fiction writing plot generation sub-plot generation fiction writing story generation scene continue storytelling fiction story science fiction romance all genres story writing vivid prosing vivid writing fiction

LFM2.5-1.2B-MEGABRAIN2-Thinking-Kimi-V2-DISTILL

This is a full deep thinking DavidAU/LFM2.5-1.2B-MEGABRAIN-Thinking-Polaris-ClaudeHOPUS-Deepseek-GLM (LFM2.5-1.2B Thinking base) fine tune using Kimi V2 reasoning dataset via Unsloth via local hardware, Linux (for windows) at 16 bit precision. The thinking / reasoning was completely replaced.

Reasoning is compact, but detailed (very detailed) and right to the "point" so to speak.

Reasoning affects:

• General model operation.
• Output generation
• Benchmarks.

Model Features:

• 128k context
• Temp range .1 to 2.5.
• Reasoning is temp stable.

IMPORTANT SETTINGS/QUANTS:

• Strongly suggest q5,q6, q8 or 16 bit precision OR Imatrix IQ3_M min.
• Rep pen 1.05 to 1.1 .

Enjoy the freedom!

BENCHMARKS:

ARC-Challenge | ARC-Easy | BoolQ | Hellaswag | OpenBookQA | PIQA  | Winogrande

0.359           0.464      0.748   0.505       0.372        0.702   0.535

VS "Normal LFM2.5"

ARC-Challenge | ARC-Easy | BoolQ | Hellaswag | OpenBookQA | PIQA  | Winogrande
0.365           0.426      0.717   0.486       0.382        0.687   0.538

---

SPECIAL THANKS TO:

• Team "TeichAI" for the excellent dataset.
• Team "Unsloth" for making the training painless.
• Team "Nightmedia" for Benchmarks and co-labing.

---

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:

https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be

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:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]