This is a full deep thinking LFM2.5-1.2B fine tune using distill reasoning dataset(s) (see lower right for dataset(s) used) 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.
This is also a Heretic model - fully uncensored. Model was first "Heretic'ed", THEN tuned.
This step by step process corrects any issues caused by de-censoring the model.
The model does what you went, when you want - no fuss, no nanny.
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 .
If you get looping during thinking, lower temp to .3 to .7
Quants lower than Q4 (non imatrix) may loop even with rep pen at 1.1 / lower temps.
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:
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:
