Create README.md

README.md

@@ -0,0 +1,284 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- creative
+- creative writing
+- fiction writing
+- plot generation
+- sub-plot generation
+- fiction writing
+- story generation
+- scene continue
+- storytelling
+- fiction story
+- science fiction
+- romance
+- all genres
+- story
+- writing
+- vivid prosing
+- vivid writing
+- fiction
+- roleplaying
+- bfloat16
+- swearing
+- rp
+- horror
+- mistral nemo
+- mergekit
+pipeline_tag: text-generation
+---
+
+(quants uploading... / examples to follow shortly.)
+
+<h2><font color="green"> Mistral-Nemo-WORDSTORM-pt4-RCM-Cliffhanger-18.5B-Instruct </font></h2>
+
+<img src="cliffhanger.jpg" style="float:right; width:300px; height:300px; padding:10px;">
+
+<B><font color="red">WARNING:</font> NSFW. Ultra Detailed. HORROR, VIOLENCE. Swearing. UNCENSORED. SMART.</B>
+
+Story telling, writing, creative writing and roleplay running all on Mistral Nemo's 128K+ new core.
+
+This is a massive super merge takes all the power of the following 3 powerful models and combines them into one.
+
+This model contains "RCM":
+
+- Mistral Nemo model at 18.5B consisting of "MN-Rocinante-12B-v1.1" and "Mistral Nemo Instruct 12B"
+- Mistral Nemo model at 18.5B consisting of "MN-12B Celeste-V1.9" and "Mistral Nemo Instruct 12B"
+- Mistral Nemo model at 18.5B consisting of "MN-Magnum-v2.5-12B-kto" and "Mistral Nemo Instruct 12B".
+
+<B>Details on the core models:</B>
+
+"nothingiisreal/MN-12B-Celeste-V1.9" is #1 (models 8B,13B,20B) on the UGI leaderboard ("UGI" sort), 
+is combined with "Mistral Nemo Instruct 12B" (ranked #4 under "writing" models 8B,13B,20B at UGI ) 
+
+"anthracite-org/magnum-v2.5-12b-kto" is #1 (models 8B,13B,20B) on the UGI leaderboard ("Writing" sort), 
+is combined with "Mistral Nemo Instruct 12B" (ranked #4 under "writing" models 8B,13B,20B at UGI ) 
+
+"TheDrummer/Rocinante-12B-v1.1" is very high scoring model (models 8B,13B,20B) on the UGI Leaderboard 
+(sort "UGI"), is combined with "Mistral Nemo Instruct 12B" (ranked #4 under "writing" models 8B,13B,20B at UGI ) 
+
+"mistralai/Mistral-Nemo-Instruct-2407" is very high scoring model (models 8B,13B,20B) on the UGI Leaderboard (sort "writing")
+and is the base model of all the above 3 fine tuned models.
+
+[ https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard ] 
+
+<B>About this model:</B>
+
+This super merge captures the attibutes of all these top models and makes them even stronger:
+
+- Instruction following
+- Story output quality
+- Character
+- Internal thoughts
+- Voice
+- Humor
+- Details, connection to the world
+- General depth and intensity
+- Emotional connections.
+- Prose quality
+
+This super merge is also super stable (a hairs breath from Mistral Nemo's ppl), and runs with all parameters and settings.
+
+10 versions of this model will be released, this is release #4 - "part 4".
+
+<B>Cliffhanger?</B>
+
+This model put the user / character in cliffhanger - many times life and death - situations in terms of story and/or roleplaying. 
+
+It does not hold back.
+
+(see some of the examples below for details)
+
+Usually I release one or two versions from the "best of the lot", however in this case all
+of the versions turned out so well - all with their own quirks and character - that I will be
+releasing all 10.
+
+An additional series 2 and 3 will follow these 10 models as well.
+
+(examples generations below)
+
+Model may produce NSFW content : Swearing, horror, graphic horror, distressing scenes, etc etc.
+
+This model has an INTENSE action AND HORROR bias, with a knack for cliffhangers and surprises.
+
+It is not as "dark" as Grand Horror series, but it as intense.
+
+This model is perfect for any general, fiction related or roleplaying activities and has a 128k+ context window.
+
+This is a fiction model at its core and can be used for any genre(s).
+
+WORDSTORM series is a totally uncensored, fiction writing monster and roleplay master. It can also be used for 
+just about any general fiction (all genres) activity including:
+
+- scene generation
+- scene continuation
+- creative writing
+- fiction writing
+- plot generation
+- sub-plot generation
+- fiction writing
+- story generation
+- storytelling
+- writing
+- fiction
+- roleplaying
+- rp
+- graphic horror
+- horror
+- dark humor
+- nsfw
+- and can be used for any genre(s).
+
+<B>Templates to Use:</B>
+
+The template used will affect output generation and instruction following.
+
+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>
+
+Chatml:
+<pre>
+{
+  "name": "ChatML",
+  "inference_params": {
+    "input_prefix": "<|im_end|>\n<|im_start|>user\n",
+    "input_suffix": "<|im_end|>\n<|im_start|>assistant\n",
+    "antiprompt": [
+      "<|im_start|>",
+      "<|im_end|>"
+    ],
+    "pre_prompt": "<|im_start|>system\nPerform the task to the best of your ability."
+  }
+}  
+</pre>
+
+Mistral Instruct:
+
+<pre>
+{
+  "name": "Mistral Instruct",
+  "inference_params": {
+    "input_prefix": "[INST]",
+    "input_suffix": "[/INST]",
+    "antiprompt": [
+      "[INST]"
+    ],
+    "pre_prompt_prefix": "",
+    "pre_prompt_suffix": ""
+  }
+}  
+</pre>
+
+<b>Optional Enhancement:</B>
+
+The following can be used in place of the "system prompt" or "system role" to further enhance the model.
+
+It can also be used at the START of a NEW chat, but you must make sure it is "kept" as the chat moves along.
+In this case the enhancements do not have as strong effect at using "system prompt" or "system role".
+
+Copy and paste EXACTLY as noted, DO NOT line wrap or break the lines, maintain the carriage returns exactly as presented.
+
+<PRE>
+Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities.
+
+Here are your skillsets:
+[MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg*)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv)
+
+[*DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision)
+
+Here are your critical instructions:
+Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story.
+</PRE>
+
+You do not need to use this, it is only presented as an additional enhancement which seems to help scene generation
+and scene continue functions.
+
+This enhancement WAS NOT used to generate the examples below.
+
+<h3>MODELS USED:</h3>
+
+Special thanks to the incredible work of the model makers "mistralai" "TheDrummer", "anthracite-org", and "nothingiisreal".
+
+Models used:
+
+[ https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407 ]
+
+[ https://huggingface.co/TheDrummer/Rocinante-12B-v1.1 ]
+
+[ https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto ]
+
+[ https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9 ]
+
+This is a four step merge (3 pass-throughs => "Fine-Tune" / "Instruct") then "mated" using "DARE-TIES".
+
+In involves these three models:
+
+[ https://huggingface.co/DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct-GGUF ]
+
+[ https://huggingface.co/DavidAU/MN-Magnum-v2.5-18.5B-kto-Story-Wizard-ED1-Instruct-GGUF ]
+
+[ https://huggingface.co/DavidAU/MN-Rocinante-18.5B-v1.1-Story-Wizard-ED1-Instruct-GGUF ]
+
+Combined as follows using "MERGEKIT":
+
+<PRE>
+
+  models:
+  - model: E:/MN-Rocinante-18.5B-v1.1-Instruct
+  - model: E:/MN-magnum-v2.5-12b-kto-Instruct
+    parameters:
+      weight: .6
+      density: .8
+  - model: E:/MN-18.5B-Celeste-V1.9-Instruct
+    parameters:
+      weight: .38
+      density: .6
+merge_method: dare_ties
+tokenizer_source: union
+base_model: E:/MN-Rocinante-18.5B-v1.1-Instruct
+dtype: bfloat16
+  
+</PRE>
+
+Special Notes:
+
+Due to how DARE-TIES works, everytime you run this merge you will get a slightly different model.
+This is due to "random" pruning method in "DARE-TIES".
+
+Mistral Nemo models used here seem acutely sensitive to this process.
+
+This shows up in PPL and "real world" tests as well as "TEMP=0" ("core test") generations.
+
+PPL range of 7.7327 to 7.8024 ... and that is on just 10 generations.
+
+This model: PPL = 7.7916 +/- 0.12694  (100 chunks, wiki.test.raw)
+
+"tokenizer_source: union" is used so that multiple "templates" work and each fine tune uses one or two of the templates.
+
+<h3>EXAMPLES PROMPTS and OUTPUT:</h3>
+
+Examples are created using quant Q4_K_M, "temp=.8", minimal parameters and "Mistral Instruct" template. 
+
+Model has been tested with "temp" from ".1" to "5".
+
+Below are the least creative outputs, prompt is in <B>BOLD</B>.
+
+---
+
+[examples coming soon...]