Update README.md

README.md

@@ -32,6 +32,8 @@ tags:
 pipeline_tag: text-generation
 ---
 
+(quants uploading...)
+
 <B><font color="red">WARNING:</font> MAY contain: Nutiness. Vivid prose. Purple Prose. Funny Violence. Over the Top Storytelling. Min of 2 eyerolls per generation. </B>
 
 <h2>M-Metaphors-Of-Madness-19.4B-GGUF - AKA "M.O.M"</h2>
@@ -81,7 +83,93 @@ IQ4XS: This might be the quant with the most difference compared to other quants
 
 Enjoy!
 
----
+<B>Brainstorm 40x</B>
+
+The BRAINSTORM process was developed by David_AU.
+
+Some of the core principals behind this process are discussed in this <a href="https://arxiv.org/pdf/2401.02415"> 
+scientific paper : Progressive LLaMA with Block Expansion </a>. 
+
+However I went in a completely different direction from what was outlined in this paper.
+
+I developed a process where the conclusion layer of a model is duplicated and calibrated, in the case of this model 40 times. 
+
+This is a delicate process, with umm... a lot of rules. 
+
+For this model in particular Brainstorm is mapped as blocks, with "intended disruption" to alter 
+and extend the power of the root model. Each layer/block interacts with each other block.
+
+(there is more going on here too, this is rough summary)
+
+The goal here is creative : prose uniqueness first and foremost.
+
+Other brainstorm methods address logic/problem solving augmentation.
+
+What is "Brainstorm" ?
+
+The reasoning center of an LLM is taken apart, reassembled, and expanded.
+
+In this case for this model: 40 times
+
+Then these centers are individually calibrated. These "centers" also interact with each other. 
+This introduces subtle changes into the reasoning process. 
+The calibrations further adjust - dial up or down - these "changes" further. 
+The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak.
+
+The core aim of this process is to increase the model's detail, concept and connection to the "world", 
+general concept connections, prose quality and prose length without affecting instruction following. 
+
+This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses.
+
+Here are some of the enhancements this process brings to the model's performance:
+
+- Prose generation seems more focused on the moment to moment. 
+- Sometimes there will be "preamble" and/or foreshadowing present.
+- Fewer or no "cliches"
+- Better overall prose and/or more complex / nuanced prose.
+- A greater sense of nuance on all levels.
+- Coherence is stronger.
+- Description is more detailed, and connected closer to the content.
+- Simile and Metaphors are stronger and better connected to the prose, story, and character.
+- Sense of "there" / in the moment is enhanced.
+- Details are more vivid, and there are more of them.
+- Prose generation length can be long to extreme.
+- Emotional engagement is stronger.
+- The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less.
+- The MORE instructions and/or details you provide the more strongly the model will respond.
+- Depending on the model "voice" may be more "human" vs original model's "voice".
+
+Other "lab" observations:
+
+- This process does not, in my opinion, make the model 5x or 10x "smarter" - if only that was true! 
+- However, a change in "IQ" was not an issue / a priority, and was not tested or calibrated for so to speak.
+- From lab testing it seems to ponder, and consider more carefully roughly speaking.
+- You could say this process sharpens the model's focus on it's task(s) at a deeper level.
+
+The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
+
+
+<B>Model Template:</B>
+
+Here is the standard Alpaca template:
+
+Alpaca:
+
+<pre>
+{
+  "name": "Alpaca",
+  "inference_params": {
+    "input_prefix": "### Instruction:",
+    "input_suffix": "### Response:",
+    "antiprompt": [
+      "### Instruction:"
+    ],
+    "pre_prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n"
+  }
+}  
+</pre>
+
+<B>Model "DNA":</B>
 
 Special thanks to model makers "jondurbin" and "MTSAIR"
 
@@ -91,8 +179,6 @@ Models Used:
 
 [ https://huggingface.co/MTSAIR/multi_verse_model ]
 
----
-
 <b>Optional Enhancement:</B>
 
 The following can be used in place of the "system prompt" or "system role" to further enhance the model.
@@ -121,7 +207,13 @@ This enhancement WAS NOT used to generate the examples below.
 
 ---
 
-FOUR EXAMPLE GENERATIONS with prompt in <B>BOLD</B>:
+<h3>EXAMPLES PROMPTS and OUTPUT:</h3>
+
+Examples are created using quant Q4_K_M, "temp=.8" (unless otherwise stated), minimal parameters and "ALPACA" template. 
+
+Model has been tested with "temp" from ".1" to "5".
+
+Below are the least creative outputs, prompt is in <B>BOLD</B>.
 
 ---