Update README.md

README.md

@@ -112,6 +112,7 @@ All information about parameters, samplers and advanced samplers applies to ALL
 QUANTS:
 -	QUANTS Detailed information.
 -	IMATRIX Quants
+-	QUANTS GENERATIONAL DIFFERENCES:
 -	ADDITIONAL QUANT INFORMATION
 -	ARM QUANTS / Q4_0_X_X
 -	NEO Imatrix Quants / Neo Imatrix X Quants
@@ -123,7 +124,7 @@ SOURCE FILES for my Models / APPS to Run LLMs / AIs:
 -	TEXT-GENERATION-WEBUI
 -	KOBOLDCPP
 -	SILLYTAVERN
--	OTHER PROGRAMS
+-	Lmstudio, Ollma, Llamacpp, and OTHER PROGRAMS
 
 TESTING / Default / Generation Example PARAMETERS AND SAMPLERS
 -	Basic settings suggested for general model operation.
@@ -212,6 +213,35 @@ The Imatrix process has NO effect on Q8 or F16 quants.
 
 F16 is full precision, just in GGUF format.
 
+QUANTS GENERATIONAL DIFFERENCES:
+
+Higher quants will have more detail, nuance and in some cases stronger "emotional" levels. Characters will also be
+more "fleshed out" too. Sense of "there" will also increase.
+
+Likewise for any use case -> higher quants nuance (both instruction following AND output generation) will be higher.
+
+"Nuance" is critical for both understanding, as well as the quality of the output generation.
+
+To put this another way, "nuance" is lost as the full precision model is more and more compressed (lower and lower quants). 
+
+Some of this can be counteracted by parameters and/or Imatrix (as noted earlier).
+
+IQ4XS / IQ4NL quants: 
+
+Due to the unusual nature of this quant (mixture/processing), generations from it will be different then other quants.
+
+These quants can also be "quanted" with or without an Imatrix.
+
+You may want to try it / compare it to other quant(s) output.
+
+Special note on Q2k/Q3 quants:
+
+You may need to use temp 2 or lower with these quants (1 or lower for q2k). Just too much compression at this level, damaging the model. 
+
+IQ quants (and Imatrix versions of q2k/q3) perform better at these "BPW" levels.
+
+Rep pen adjustments may also be required to get the most out a model at this/these quant level(s).
+
 ADDITONAL QUANT INFORMATION:
 
 <details>
@@ -371,7 +401,7 @@ For reference here are some Class 3/4 models:
 
 [ https://huggingface.co/DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-23.5B-GGUF ]
 
-(note Grand Guttenberg Madness/Darkess (12B) are class 1 models, but compressed versions of 23.5B)
+(note Grand Guttenberg Madness/Darkness (12B) are class 1 models, but compressed versions of 23.5B)
 
 Although Class 3 and Class 4 models will work when used within their specific use case(s), standard parameters and settings on the model card, I recognize that users want either a smoother experience
 and/or want to use these models for other than intended use case(s) and that is in part why I created this document. 
@@ -533,13 +563,11 @@ Note for Class 3/Class 4 models settings/samplers (discussed below) "repeat-last
 
 Now that you have the basic parameters and samplers from the previous section, I will cover Generational Control and Steering.
 
-This section is optional.
+This section is optional and covers how to manually STEER generation(s) - ANY MODEL, ANY TYPE.
 
-This section (in part) will cover how to deal with Class 3/4 issues directly, as well as general issues than can happen with any "class" of model during generation IF you want to control them manually as
+This section (in part) will also cover how to deal with Class 3/4 model issues directly, as well as general issues than can happen with any "class" of model during generation IF you want to control them manually as
 the "Quick Reference" and/or "Detailed Parameters, Samplers, and Advanced Samplers" will cover how to deal with any generation issue(s) automatically.
 
-This section will also cover how to manually STEER generation(s) - ANY MODEL, ANY TYPE.
-
 There is a very important concept that must be covered first:
 
 The output/generation/answer to your prompt/instructions BECOMES part of your "prompt" after you click STOP, and then click on "CONTINUE".
@@ -552,7 +580,7 @@ When you hit "REGEN" this nullifies only the last "generation" - not the prompt
 
 The part I will cover here is once a generation has started, from a single prompt (no other prompts/generations in the chat).
 
-So lets start with a prompt (NOTE: this one has no steering in the instructions):
+So lets start with a prompt (NOTE: this prompt has no "steering" in the instructions):
 
 Start a 1000 word scene (vivid horror, 1st person, include thoughts) with: The sky scraper swayed, as she watched the window in front of her on the 21 floor explode...
 
@@ -590,6 +618,7 @@ These methods apply to all generation types - not just a "scene" or "story", but
 
 Notes: 
 - For Text Generation Webui, you can transfer your "chat" to "notebook" for easy Stop/Edit/Continue function.
+- For KoboldCPP -> This is built in.
 - For Silly Tavern -> This is built in.
 - For LMStudio -> This is built in.
 - For API (direct control) you have to send the "chat" elements back to the "server" with the "edits" (send the whole "revised" chat as a json payload).
@@ -616,7 +645,19 @@ If you have single or multiple paragraph repeat(s):
 - Hit continue. 
 - Better: Do these steps, and add "steering" (last line -> word, phrase, sentence or paragraph)
 
-In each case we are BREAKING the "condition" that lead (or lead into) to the repeat(s).
+In each case we are BREAKING the "condition(s)" that lead (or lead into) to the repeat(s).
+
+If you have "rants" and/or "model has lost its mind":
+
+- Stop generation, edit out all the paragraph(s), and back AS FAR as possible to where is appears the rant/mind loss occured (delete ALL) and delete one additional paragraph / 2 or more sentences.
+- Hit continue. 
+- Better: Do these steps, and add "steering" (last line -> word, phrase, sentence or paragraph). 
+
+Class 3/4 model additional note:
+
+With these classes of model, you MAY need to "edit" / "revise" further back than one or two lines / one paragraph - they sometimes need just a little more editing.
+
+Another option is using "Cold" Editing/Generation explained below.
 
 <B>Advanced Steering / Fixing Issues (any model, any type) and "sequenced" parameter/sampler change(s)</B>
 
@@ -671,16 +712,18 @@ You may want to modify the instructions to provide a "steering" continue point a
 
 ---
 
-Compiled by: "EnragedAntelope"
-
-https://huggingface.co/EnragedAntelope
-
-https://github.com/EnragedAntelope
+Compiled by: "EnragedAntelope" ( https://huggingface.co/EnragedAntelope  || https://github.com/EnragedAntelope )
 
 This section will get you started - especially with class 3 and 4 models - and the detail section will cover settings / control in more depth below.
 
 Please see sections below this for advanced usage, more details, settings, notes etc etc.
 
+IMPORTANT NOTES: 
+
+Not all parameters, samplers and advanced samplers are listed in this quick reference section. Scroll down to see all of them in following sections.
+
+Likewise there may be some "name variation(s)" - in other LLM/AI apps - this is addressed in the detailed sections.
+
 <small>
 # LLM Parameters Reference Table
 
@@ -736,7 +779,7 @@ Please see sections below this for advanced usage, more details, settings, notes
 
 | **Advanced Samplers** |
 
-| dry_multiplier 		| Controls DRY (Don't Repeat Yourself) intensity. Range: 0.8-1.12+ |
+| dry_multiplier 		| Controls DRY (Don't Repeat Yourself) intensity. Range: 0.8-1.12+ Class 3 (Class 4 is higher) |
 
 | dry_allowed_length | Allowed length for repeated sequences in DRY. Default: 2 |
 
@@ -749,14 +792,22 @@ Please see sections below this for advanced usage, more details, settings, notes
 
 ## Notes
 
-- For Class 3 and 4 models, using both DRY and Quadratic sampling is recommended
+- For Class 3 and 4 models, using both DRY and Quadratic sampling is recommended (see advanced/detailed samplers below on how to control the model here directly)
 - Lower quants (Q2K, IQ1s, IQ2s) may require stronger settings due to compression damage
 - Parameters interact with each other, so test changes one at a time
 - Always test with temperature at 0 first to establish a baseline
 
 </small>
 
-IMPORTANT: Make sure to review MIROSTAT sampler settings below, due to behaviour of this specific sampler / affect on parameters/other samplers.
+CLASS 3/4 Models:
+
+If you are using a class 3 or class 4 model for use case(s) such as role play, multi-turn, chat etc etc, it is suggested to activate / set all samplers for class 3 but may be required for class 4 models.
+
+Likewise for fine control of a class 3/4 via "DRY" and "Quadratic" samplers is detailed below. These allow you to dial up or dial down the model's raw power directly.
+
+MICROSTAT Sampler - IMPORTANT: 
+
+Make sure to review MIROSTAT sampler settings below, due to behaviour of this specific sampler / affect on parameters/other samplers which varies from app to app too.
 
 ---
 
@@ -935,7 +986,11 @@ Generally this is not used.
 
 In some AI/LLM apps, these may only be available via JSON file modification and/or API.
 
-For "text-gen-webui" and "Koboldcpp" these are directly accessible (and via Sillytavern IF you use either of these APPS to connect Silly Tavern to their API).
+For "text-gen-webui", "Koboldcpp"  these are directly accessible ; other programs/app this varies. 
+
+Sillytavern: 
+
+If the apps support (Sillytavern is connected to via API) these parameters/samplers then you can access them via Silly Tavern's parameter/sampler panel. So if you are using Text-Gen-Webui, Koboldcpp, LMStudio, Llamacpp, Ollama (etc) you can set/change/access all or most of these.
 
 <B>i) OVERALL GENERATION CHANGES (affect per token as well as over all generation):</B>
 
@@ -1083,7 +1138,7 @@ Careful testing is required, as this can have unclear side effects.
 
 Note #1 : 
 
-You can use these samplers via Sillytavern IF you use either of these APPS (Koboldcpp/Text Generation Webui) to connect Silly Tavern to their API.
+You can use these samplers via Sillytavern IF you use either of these APPS (Koboldcpp/Text Generation Webui/App supports them) to connect Silly Tavern to their API.
 
 Other Notes:
 
@@ -1112,8 +1167,8 @@ However, you should also check / test operation of (these are in Text Generation
 a] Affects per token generation:
 
 - top_a
-- epsilon_cutoff - see note 4
-- eta_cutoff - see note 4
+- epsilon_cutoff - see note #4
+- eta_cutoff - see note #4
 - no_repeat_ngram_size - see note #1.
 
 b] Affects generation including phrase, sentence, paragraph and entire generation:
@@ -1227,6 +1282,8 @@ Hopefully this powerful sampler will soon appear in all LLM/AI apps.
 
 You can access this in the KoboldCPP app, under "context" -> "tokens" on the main page of the app after start up.
 
+You can also access in SillyTavern if you use KoboldCPP as your "API" connected app too.
+
 This sampler allows banning words and phrases DURING generation, forcing the model to "make another choice".
 
 This is a game changer in custom real time control of the model.