Konnect1221 commited on
Commit
ddecc0d
·
verified ·
1 Parent(s): 577d055

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -18
README.md CHANGED
@@ -1,39 +1,42 @@
1
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647aa776555b5e199c012d76/ezXwmj1uPJ3XLb-BSdGnB.png)
2
 
3
 
4
- **Methception 1.4 and LLamaception 1.4: A New Level of Roleplay**
5
- Welcome to the twin peaks of roleplay presets—the sweet sauce of immersive storytelling now comes in two flavors. Whether you're rocking Mistral-based models or Llama 3.3 70B beasts, you can sprinkle that inception-like secret sauce to craft scenes that feel real, robust, and downright addictive.
6
 
7
  ---
8
 
9
- ### A Tale of Two Templates
10
 
11
- #### Methception 1.4
12
- Methception is the classic high-octane preset designed for Mistral-based models using the Metharme prompt format. It’s already proven its mettle with fine-tunes like **Drummers Behemoth 1.2** and **MortalWombat’s Monstral V2**, adding layers of spatial awareness, emotional tension, and dynamic pacing. It keeps your roleplay rolling smoothly while providing a blend of positive, neutral, and negative biases that evoke genuine agency among characters.
13
 
14
- #### LLamaception 1.4
15
- LLamaception is Methception’s brand-new sibling, tailored for models built on **Llama 3.3 70B**. It packs the same delicious sauce but optimized for fine-tunes like **Drummers Anubis**, **Steelskulls Evalibis & Evayale**, and the mind-bending brilliance of **Eva-Unit/Sao10k**. Expect the same focus on sensory immersion, nuanced emotional arcs, and cinematic pacing—just recalibrated for the power of Llama-based architecture.
 
 
 
16
 
17
  ---
18
 
19
- ### What’s New in Methception 1.4 (and LLamaception 1.4)?
20
 
21
- #### Enhanced Continuity with Instruction 8
22
- The big star of this update is **Instruction 8**, which doubles down on maintaining a logical flow across multiple scenes. Whether you’re sniffing out faint aromas of spices in Methception or bridging tension from earlier chapters in LLamaception, Instruction 8 teaches the AI how to recall and build on previously mentioned details—making your roleplay smoother and more cohesive.
23
 
24
- #### May I Have Extra Sauce, Please?” Last Assistant Prefix
25
- To tackle limited System Prompt support across both Mistral and Llama powerhouses, we’ve introduced the **Last Assistant Prefix**. Before spinning up a new response, the model re-reads the context and instructions, making sure everything stays tight-knit and dripping with that inception-like sauce 🤌. No matter how deep or complex your world-building goes, your AI remains consistent and coherent.
26
 
27
- #### Improved Markdown Formatting
28
- Both **Methception** and **LLamaception** templates now rock a restructured Context Template with crisp markdown headings and end marks. Cleaner formatting means better readability for you and improved structural parsing for the AI—win-win!
29
 
30
- #### Strengthened the “Show, Don’t Tell” Philosophy
31
- We’re not just preaching about continuity; we’re living it. **Instruction 8** demonstrates its own approach by actively referencing earlier context as it explains how to apply continuity. It’s meta in the best way possible, helping the model practice what it preaches.
32
 
33
  ---
34
 
35
- ### Why It Matters
36
- With **Methception 1.4** and **LLamaception 1.4**, you get a synergy of clarity and depth that will catch you by surprisein a good way. The new instruction set, formatting improvements, and context-handling enhancements all culminate in deeply immersive roleplay. Whether you’re diving into a gritty, character-driven saga or cozying up with your waifu in a dreamy slice-of-life scenario, these templates hit like a euphoric, "quantized" dream.
37
 
38
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647aa776555b5e199c012d76/AGj6KvmrIr6A0SJcMA0Jg.png)
39
 
 
1
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647aa776555b5e199c012d76/ezXwmj1uPJ3XLb-BSdGnB.png)
2
 
3
 
4
+ **Methception 1.4, LLamaception 1.4, and Finally Introducing Qwenception 1.4: A New Level of Roleplay**
5
+ Get ready to indulge in three distinct flavors of inception-like secret sauce. Whether youre rolling with Mistral-based models, Llama 3.3 70B beasts, or Qwen 2.5/coder wizards, these Ception presets bring the heat without losing that chill vibe. Picture a smooth, quantized dreamscape that pulls you in with deep storytelling, real immersion, and on-point energy.
6
 
7
  ---
8
 
9
+ ## A Trio of Templates
10
 
11
+ ### **Methception 1.4**
12
+ **Methception** is our OG powerhouse built for Mistral-based models using the Metharme prompt format. It’s already proven its might with fine-tunes like **Drummers Behemoth 1.2** and **MortalWombat’s Monstral V2**, layering spatial awareness, emotional undercurrents, and cinematic pacing. The result? Characters who spring to life, fueled by a balanced mix of positive, neutral, and negative biases that make every scenario pop.
13
 
14
+ ### **LLamaception 1.4**
15
+ Its sibling, **LLamaception**, is tailored for models running **Llama 3.3 70B**. You’ll get the same secret sauce but fine-tuned for **Drummers Anubis**, **Steelskulls Evalibis & Evayale**, and the mind-bending punch of **Eva-Unit/Sao10k**. Expect equally rich storytelling, emotional depth, and crisp pacing—optimized for the Llama architecture.
16
+
17
+ ### **Finally Introducing Qwenception 1.4**
18
+ Rounding out the trifecta is **Qwenception**, crafted for **Qwen 2.5/coder models**. It pairs perfectly with fine-tunes like **Evathene by sophosympatheia** and **Chuluun by Datoad**, letting you blend code-savvy insights with cinematic flair. Look forward to vivid emotions, seamless continuity, and that same immersive energy, tuned specifically for Qwen’s style.
19
 
20
  ---
21
 
22
+ ## What’s New Across Methception, LLamaception, and Qwenception 1.4?
23
 
24
+ ### **Enhanced Continuity with Instruction 8**
25
+ All three Ception presets now feature a boosted sense of continuity, thanks to **Instruction 8**. Whether you’re tracking down faint spice aromas in Methception, bridging emotional threads in LLamaception, or recalling code snippets in Qwenception, the AI keeps past details at the forefront to make every scene feel cohesive and genuine.
26
 
27
+ ### **“May I Have Extra Sauce, Please?” (Last Assistant Prefix)**
28
+ System Prompt support can be limited, but **Last Assistant Prefix** helps each model—Mistral, Llama, or Qwen—revisit context and instructions before crafting the next response. This keeps everything drenched in that juicy, inception-like sauce, ensuring no detail goes astray no matter how deep your worldbuilding or coding adventure runs.
29
 
30
+ ### **Improved Markdown Formatting**
31
+ All three templates benefit from a refreshed Context Template, now featuring clear markdown headings and end markers. This not only improves readability but also helps the AI parse structure more effectively.
32
 
33
+ ### **Strengthened “Show, Don’t Tell” Philosophy**
34
+ We dont just talk about continuity, we demonstrate it. **Instruction 8** uses its own guidelines while guiding the AI to maintain logical flow across scenes. This self-referential approach turns your roleplay sessions into a seamless journey, where each narrative beat naturally builds on the last.
35
 
36
  ---
37
 
38
+ ## Why It Matters
39
+ When clarity, depth, and immersion are baked into every line, your roleplay becomes an unforgettable ride. These Ception presetsMethception for Mistral, LLamaception for Llama, and Qwenception for Qwen—deliver a potent mix of “meth”-like intensity wrapped in an inception-flavored dream. With updated instructions, polished formatting, and supercharged context handling, you’ll find yourself riding a creative high that keeps on giving. Strap in, tap into your imagination, and let’s cook up something legendary.
40
 
41
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/647aa776555b5e199c012d76/AGj6KvmrIr6A0SJcMA0Jg.png)
42