Update README.md

README.md

@@ -1,3 +1,158 @@
----
-license: apache-2.0
----
+
+---
+license: apache-2.0
+language:
+- en
+---
+
+<div align="center">
+  <b style="font-size: 40px;">Impish_Mind_8B</b>
+
+
+</div>
+
+
+<img src="https://huggingface.co/SicariusSicariiStuff/Impish_Mind_8B/resolve/main/Images/Impish_Mind.png" alt="Impish_Mind_8B" style="width: 70%; min-width: 500px; display: block; margin: auto;">
+
+"As she laid her head on the snow-white pillow, no rest was graced upon her thoughts.
+
+Her impish mind wandered about like the mischievous sprite that it was, her in-dream words laced with such impish cleverness that even a trickster god might have paused to take his notes.
+
+Every impish flicker of her lips, her tail, it spoke of schemes—lascivious, a night of naughty dreams.
+
+Woven with the silken thread of lascivious deeds indeed. There was no mistaking of her bright—it was an impish mind, and of that, I'm sure all right..."
+
+---
+
+## Model Details
+
+- Intended use: **Role-Play**, **Creative Writing**, **General Tasks**.
+
+- Censorship level: <b>Medium - Low</b>
+
+- X / 10 (10 completely uncensored)
+
+---
+
+- UGI score:
+
+### Awaiting results
+
+---
+
+This model was trained using a different approach and data, it will likely be more censored but should be **much much smarter**. This model card will be updated soon. Submitted for evals.
+
+
+# Model instruction template: Llama-3-Instruct
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+{output}<|eot_id|>
+```
+
+**Recommended generation Presets:**
+
+<details>
+<summary><b>Midnight Enigma</b></summary>
+  max_new_tokens: 512
+
+  temperature: 0.98
+
+  top_p: 0.37
+
+  top_k: 100
+
+  typical_p: 1
+
+  min_p: 0
+
+  repetition_penalty: 1.18
+
+  do_sample: True
+
+</details>
+
+<details>
+<summary><b>min_p</b></summary>
+  max_new_tokens: 512
+
+  temperature: 1
+
+  top_p: 1
+
+  top_k: 0
+
+  typical_p: 1
+
+  min_p: 0.05
+
+  repetition_penalty: 1
+
+  do_sample: True
+
+</details>
+
+<details>
+<summary><b>Divine Intellect</b></summary>
+  max_new_tokens: 512
+
+  temperature: 1.31
+
+  top_p: 0.14
+
+  top_k: 49
+
+  typical_p: 1
+
+  min_p: 0
+
+  repetition_penalty: 1.17
+
+  do_sample: True
+
+</details>
+
+<details>
+<summary><b>simple-1</b></summary>
+  max_new_tokens: 512
+
+  temperature: 0.7
+
+  top_p: 0.9
+
+  top_k: 20
+
+  typical_p: 1
+
+  min_p: 0
+
+  repetition_penalty: 1.15
+
+  do_sample: True
+
+</details>
+
+---
+
+### Support
+<img src="https://i.imgur.com/0lHHN95.png" alt="GPUs too expensive" style="width: 10%; min-width: 100px; display: block; margin: left;">
+
+- [My Ko-fi page](https://ko-fi.com/sicarius) ALL donations will go for research resources and compute, every bit is appreciated 🙏🏻
+
+---
+
+## Benchmarks
+
+**SOON**
+
+---
+
+## Other stuff
+- [Blog and updates](https://huggingface.co/SicariusSicariiStuff/Blog_And_Updates) Some updates, some rambles, sort of a mix between a diary and a blog.
+- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector.
+- [LLAMA-3_8B_Unaligned](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned) The grand project that started it all.