Update README.md

README.md

@@ -39,7 +39,7 @@ This settings can also fix a number of model issues (any model) such as:
 
 Likewise ALL the setting below can also improve model generation and/or general overall "smoothness" / "quality" of model operation.
 
-Even if you are not using my models, you may find this document useful for any model available online.
+Even if you are not using my models, you may find this document useful for any model (any quant / full source) available online.
 
 If you are currently using model(s) that are difficult to "wrangle" then apply "Class 3" or "Class 4" settings to them.
 
@@ -47,6 +47,18 @@ This document will be updated over time too.
 
 Please use the "community tab" for suggestions / edits / improvements.
 
+IMPORTANT:
+
+Every parameter, sampler and advanced sampler here affects per token generation and overall generation quality.
+
+This effect is cumulative especially with long output generation and/or multi-turn (chat, role play, COT).
+
+Likewise because of how modern AIs/LLMs operate the previously generated (quality) of the tokens generated
+affect the next tokens generated too.
+
+You will get higher quality operation overall - stronger prose, better answers, and a higher quality adventure.
+
+
 ------------------------------------------------------------------------------------------------------------------------------------------------------------
 PARAMETERS AND SAMPLERS
 ------------------------------------------------------------------------------------------------------------------------------------------------------------
@@ -162,6 +174,8 @@ Keep in mind the biggest parameter / random "unknown" is your prompt.
 
 A word change, rephrasing, punctation , even a comma, or semi-colon can drastically alter the output, even at min temp settings. CAPS also affect generation too.
 
+Likewise the size, and complexity of your prompt impacts generation too ; especially clarity and direction.
+
 <B>temp  /  temperature</B>
 
 temperature (default: 0.8)
@@ -180,6 +194,8 @@ top-p sampling (default: 0.9, 1.0 = disabled)
 
 If not set to 1, select tokens with probabilities adding up to less than this number. Higher value = higher range of possible random results.
 
+Dropping this can simplify word choices but this works in conjunction with "top-k"
+
 I use default of: .95 ; 
 
 <B>min-p</B>                               	
@@ -190,6 +206,8 @@ Tokens with probability smaller than (min_p) * (probability of the most likely t
 
 I use default: .05 ; 
 
+Careful adjustment of this parameter can result in more "wordy" or "less wordy" generation but this works in conjunction with "top-k".
+
 <B>top-k</B>                               		
 
 top-k sampling (default: 40, 0 = disabled)
@@ -198,32 +216,40 @@ Similar to top_p, but select instead only the top_k most likely tokens. Higher v
 
 Bring this up to 80-120 for a lot more word choice, and below 40 for simpler word choices.
 
-NOTES:
+As this parameter operates in conjection with "top-p" and "min-p" all three should be carefully adjusted one at a time.
+
+<B>NOTE - "CORE" Testing with "TEMP":</B>
 
 For an interesting test, set "temp" to 0 ; this will give you the SAME generation for a given prompt each time. 
 
-Then adjust a word, phrase, sentence etc - to see the differences.
+Then adjust a word, phrase, sentence etc in your prompt, and generate again to see the differences.
+
+(you should use a "fresh" chat for each generation)
 
 Keep in mind this will show model operation at its LEAST powerful/creative level and should NOT be used to determine if the model works for your use case(s).
 
-Then test "at temp" to see the model in action. (5-10 generations recommended)
+Then test your prompt(s) "at temp" to see the model in action. (5-10 generations recommended)
 
-You can also use "temp=0" to test different quants of the same model to see generation differences. (roughly "BIAS").
+You can also use "temp=0" to test different quants of the same model to see generation differences. (roughly minor "BIAS" changes which reflect math changes due to compress/mixtures differences between quants).
 
-Another option is testing different models (of the same quant) to see how each handles your prompt(s).
+Another option is testing different models (at temp=0 AND of the same quant) to see how each handles your prompt(s).
 
-Then test "at temp" to see the MODELS in action. (5-10 generations recommended)
+Then test "at temp" with your prompt(s) to see the MODELS in action. (5-10 generations recommended)
 
 
 ------------------------------------------------------------------------------
 PENALITY SAMPLERS:
 ------------------------------------------------------------------------------
 
-These samplers "trim" or "prune" output in real time. The longer the generation, the stronger overall effect.
+These samplers "trim" or "prune" output in real time. 
+
+The longer the generation, the stronger overall effect but that all depends on "repeat-last-n" setting.
+
+For creative use cases, these samplers can alter prose generation in interesting ways.
 
 CLASS 4: For these models it is important to activate / set all samplers as noted for maximum quality and control.
 
-PRIMARY:
+<B>PRIMARY:</B>
 
 <B>repeat-last-n</B>                       	
 
@@ -240,7 +266,7 @@ This setting also works in conjunction with all other "rep pens" below.
 
 This parameter is the "RANGE" of tokens looked at for the samplers directly below.
 
-SECONDARIES:
+<B>SECONDARIES:</B>
 
 <B>repeat-penalty</B>