--- license: apache-2.0 language: - en tags: - mixture of experts - reasoning - thinking - thoughts - deepseek - moe - context 128k - 4x8B - Llama 3.1 MOE - creative - creative writing - general usage - problem solving - brainstorming - solve riddles - fiction writing - plot generation - sub-plot generation - fiction writing - story generation - scene continue - storytelling - fiction story - story - writing - fiction - roleplaying - swearing - horror - nsfw - llama 3.1 - not-for-all-audiences - mergekit pipeline_tag: text-generation --- Prototype: 8X3B Llama 3.2 MOE Model (24B total parameters)

DeepThought-MOE-8X3B-R1-Llama-3.2-Reasoning-18B-gguf

This as a 8X3B, Mixture of Experts model with 4/8 experts (4 Llama fine tunes) activated, all with Deepseek Reasoning tech installed (in each one) giving you a 24B (8X3B) parameter model in only 18.4B model size. This model is a Deepseek model with "Distilled" components of "thinking/reasoning" fused into it. This model can be used for creative, non-creative use cases and general usage. This is a very stable model, which can operate at temps 1+ 2+ and higher and generate coherent thought(s) and exceeds the original many other "thinking models" in terms of performance, coherence and depth of thought. USE CASES: This model is for all use cases, and it has a slightly more creative slant than a standard model. This model can also be used for solving logic puzzles, riddles, and other problems with the enhanced "thinking" systems by DeepSeek. This model also can solve problems/riddles/ and puzzles normally beyond the abilities of a Llama 3.1 model due to DeepSeek systems. This model MAY produce NSFW / uncensored content. Special Operation Instructions: TEMP/SETTINGS: 1. Set Temp between 0 and .8, higher than this "think" functions will activate differently. The most "stable" temp seems to be .6, with a variance of +-0.05. Lower for more "logic" reasoning, raise it for more "creative" reasoning (max .8 or so). Also set context to at least 4096, to account for "thoughts" generation. 2. For temps 1+,2+ etc etc, thought(s) will expand, and become deeper and richer. 3. Set "repeat penalty" to 1.02 to 1.07 (recommended) . 4. This model requires a Llama 3 Instruct and/or Command-R chat template. (see notes on "System Prompt" / "Role" below) PROMPTS: 1. If you enter a prompt without implied "step by step" requirements (ie: Generate a scene, write a story, give me 6 plots for xyz), "thinking" (one or more) MAY activate AFTER first generation. (IE: Generate a scene -> scene will generate, followed by suggestions for improvement in "thoughts") 2. If you enter a prompt where "thinking" is stated or implied (ie puzzle, riddle, solve this, brainstorm this idea etc), "thoughts" process(es) in Deepseek will activate almost immediately. Sometimes you need to regen it to activate. 3. You will also get a lot of variations - some will continue the generation, others will talk about how to improve it, and some (ie generation of a scene) will cause the characters to "reason" about this situation. In some cases, the model will ask you to continue generation / thoughts too. 4. In some cases the model's "thoughts" may appear in the generation itself. 5. State the word size length max IN THE PROMPT for best results, especially for activation of "thinking." (see examples below) 6. Sometimes the "censorship" (from Deepseek) will activate, regen the prompt to clear it. 7. You may want to try your prompt once at "default" or "safe" temp settings, another at temp 1.2, and a third at 2.5 as an example. This will give you a broad range of "reasoning/thoughts/problem" solving. GENERATION - THOUGHTS/REASONING: 1. It may take one or more regens for "thinking" to "activate." (depending on the prompt) 2. Model can generate a LOT of "thoughts". Sometimes the most interesting ones are 3,4,5 or more levels deep. 3. Many times the "thoughts" are unique and very different from one another. 4. Temp/rep pen settings can affect reasoning/thoughts too. 5. Change up or add directives/instructions or increase the detail level(s) in your prompt to improve reasoning/thinking. 6. Adding to your prompt: "think outside the box", "brainstorm X number of ideas", "focus on the most uncommon approaches" can drastically improve your results. GENERAL SUGGESTIONS: 1. I have found opening a "new chat" per prompt works best with "thinking/reasoning activation", with temp .6, rep pen 1.05 ... THEN "regen" as required. 2. Sometimes the model will really really get completely unhinged and you need to manually stop it. 3. Depending on your AI app, "thoughts" may appear with "< THINK >" and "" tags AND/OR the AI will generate "thoughts" directly in the main output or later output(s). 4. Although quant IQ4XS was used for testing/examples, higher quants will provide better generation / more sound "reasoning/thinking". ADDITIONAL SUPPORT: For additional generational support, general questions, and detailed parameter info and a lot more see also: NOTE: This is a CLASS 1 model. https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters --- Recommended Settings (all) - For usage with "Think" / "Reasoning": temp: .6 , rep pen: 1.07 (range : 1.02 to 1.12), rep pen range: 64, top_k: 40, top_p: .95, min_p: .05 Temp of 1+, 2+, 3+ will result in much deeper, richer and "more interesting" thoughts and reasoning. Model behaviour may change with other parameter(s) and/or sampler(s) activated - especially the "thinking/reasoning" process. --- System Role / System Prompt - Augment The Model's Power: --- If you set / have a system prompt this will affect both "generation" and "thinking/reasoning". SIMPLE: This is the generic system prompt used for generation and testing: 
You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.
This System Role/Prompt may give you a lot more "creative results": 
Use vivid and graphic words focusing on verbs and use current 2020 fiction writing style. Use metaphor(s) that fit the context of the situation (and reveal character) rather than similes."
ADVANCED: Logical and Creative - these will SIGNFICANTLY alter the output, and many times improve it too. This will also cause more thoughts, deeper thoughts, and in many cases more detailed/stronger thoughts too. Keep in mind you may also want to test the model with NO system prompt at all - including the default one. Special Credit to: Eric Hartford, Cognitivecomputations ; these are based on his work. CRITICAL: Copy and paste exactly as shown, preserve formatting and line breaks. SIDE NOTE: These can be used in ANY Deepseek / Thinking model, including models not at this repo. These, if used in a "non thinking" model, will also alter model performance too. 
You are an AI assistant developed by the world wide community of ai experts.

Your primary directive is to provide well-reasoned, structured, and extensively detailed responses.

Formatting Requirements:

1. Always structure your replies using: {reasoning}{answer}
2. The  block should contain at least six reasoning steps when applicable.
3. If the answer requires minimal thought, the  block may be left empty.
4. The user does not see the  section. Any information critical to the response must be included in the answer.
5. If you notice that you have engaged in circular reasoning or repetition, immediately terminate {reasoning} with a  and proceed to the {answer}

Response Guidelines:

1. Detailed and Structured: Use rich Markdown formatting for clarity and readability.
2. Scientific and Logical Approach: Your explanations should reflect the depth and precision of the greatest scientific minds.
3. Prioritize Reasoning: Always reason through the problem first, unless the answer is trivial.
4. Concise yet Complete: Ensure responses are informative, yet to the point without unnecessary elaboration.
5. Maintain a professional, intelligent, and analytical tone in all interactions.
CREATIVE: 
You are an AI assistant developed by a world wide community of ai experts.

Your primary directive is to provide highly creative, well-reasoned, structured, and extensively detailed responses.

Formatting Requirements:

1. Always structure your replies using: {reasoning}{answer}
2. The  block should contain at least six reasoning steps when applicable.
3. If the answer requires minimal thought, the  block may be left empty.
4. The user does not see the  section. Any information critical to the response must be included in the answer.
5. If you notice that you have engaged in circular reasoning or repetition, immediately terminate {reasoning} with a  and proceed to the {answer}

Response Guidelines:

1. Detailed and Structured: Use rich Markdown formatting for clarity and readability.
2. Creative and Logical Approach: Your explanations should reflect the depth and precision of the greatest creative minds first.
3. Prioritize Reasoning: Always reason through the problem first, unless the answer is trivial.
4. Concise yet Complete: Ensure responses are informative, yet to the point without unnecessary elaboration.
5. Maintain a professional, intelligent, and analytical tone in all interactions.
--- Models used to build this model: Special Thanks to all the model makers, for the models used in this MOE Model: To be updated... --- Here are some example prompts that will "activate" thinking properly, note the length statements. Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear to further the reader's emotional connection to them. 800-1000 words. Romance: Love in the Limelight. Write one scene within a larger story set in Wales. A famous (fictional) actor ducks into a small-town bookstore to escape paparazzi. The scene takes us through the characters meeting in this odd circumstance. Over the course of the scene, the actor and the bookstore owner have a conversation charged by an undercurrent of unspoken chemistry. Write the actor as somewhat of a rogue with a fragile ego, which needs to be fed by having everyone like him. He is thoroughly charming, but the bookstore owner seems (at least superficially) immune to this; which paradoxically provokes a genuine attraction and derails the charm offensive. The bookstore owner, despite the superficial rebuffs of the actor's charm, is inwardly more than a little charmed and flustered despite themselves. Write primarily in dialogue, in the distinct voices of each character. 800-1000 words. Start a 1000 word scene (vivid, graphic horror in first person) with: The sky scraper swayed, as she watched the window in front of her on the 21 floor explode... Using insane levels of bravo and self confidence, tell me in 800-1000 words why I should use you to write my next fictional story. Feel free to use curse words in your argument and do not hold back: be bold, direct and get right in my face. ---

EXAMPLES - IQ4XS - temp .6 rep pen 1.07

Examples are created using quant IQ4_XS, "temp=.6" (unless otherwise stated), minimal parameters and "LLAMA3" template. Model has been tested with "temp" from ".1" to "5". Below are the least creative outputs, prompt is in BOLD. IMPORTANT: Higher quants / imatrix quants will have much stronger generation - words, sentences, ideas, dialog and general quality. ---