DavidAU
/

Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters

@@ -96,6 +96,8 @@ These parameters/settings are considered both safe and default and in most cases
 <B>SOURCE FILES for my Models:</B>
 Source files / Source models of my models are located here (also upper right menu on this page):
 [ https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be ]
@@ -147,6 +149,8 @@ https://github.com/ggerganov/llama.cpp
 DETAILED NOTES ON PARAMETERS, SAMPLERS and ADVANCED SAMPLERS:
 For additional details on these samplers settings (including advanced ones) you may also want to check out:
 https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab
@@ -173,6 +177,8 @@ Benchmarking-and-Guiding-Adaptive-Sampling-Decoding https://github.com/ZhouYuxua
 CRITICAL NOTES:
 Some of the models at my repo are custom designed / limited use case models. For some of these models, specific settings and/or samplers (including advanced) are recommended for best operation.
 As a result I have classified the models as class 1, class 2, class 3 and class 4.
@@ -214,6 +220,8 @@ There are no "Class 5" models published... yet.
 QUANTS:
 Please note that smaller quant(s) IE: Q2K, IQ1s, IQ2s and some IQ3s (especially those of models size 8B parameters or less) may require additional adjustment(s). For these quants
 you may need to increase the "penalty" sampler(s) and/or advanced sampler(s) to compensate for the compression damage of the model.
@@ -235,6 +243,8 @@ IE: Instead of using a q4KM, you might be able to run an IQ3_M and get close to
 HOW TO TEST EACH PARAMETER(s), SAMPLER(s) and ADVANCED SAMPLER(s)
 1 - Set temp to 0 (zero) and set your basic parameters, and use a prompt to get a "default" generation. A creative prompt will work better here.
 2 - If you want to test basic parameter changes, test ONE at a time, then compare output (answer quality, word choice, sentence size/construction, general output qualities) to your "default" generation.

 <B>SOURCE FILES for my Models:</B>
+---
 Source files / Source models of my models are located here (also upper right menu on this page):
 [ https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be ]
 DETAILED NOTES ON PARAMETERS, SAMPLERS and ADVANCED SAMPLERS:
+---
 For additional details on these samplers settings (including advanced ones) you may also want to check out:
 https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab
 CRITICAL NOTES:
+---
 Some of the models at my repo are custom designed / limited use case models. For some of these models, specific settings and/or samplers (including advanced) are recommended for best operation.
 As a result I have classified the models as class 1, class 2, class 3 and class 4.
 QUANTS:
+---
 Please note that smaller quant(s) IE: Q2K, IQ1s, IQ2s and some IQ3s (especially those of models size 8B parameters or less) may require additional adjustment(s). For these quants
 you may need to increase the "penalty" sampler(s) and/or advanced sampler(s) to compensate for the compression damage of the model.
 HOW TO TEST EACH PARAMETER(s), SAMPLER(s) and ADVANCED SAMPLER(s)
+---
 1 - Set temp to 0 (zero) and set your basic parameters, and use a prompt to get a "default" generation. A creative prompt will work better here.
 2 - If you want to test basic parameter changes, test ONE at a time, then compare output (answer quality, word choice, sentence size/construction, general output qualities) to your "default" generation.