---
license: apache-2.0
language:
- en
base_model: SicariusSicariiStuff/Impish_Mind_8B
tags:
- llama-cpp
- gguf-my-repo
---

# Triangle104/Impish_Mind_8B-Q5_K_S-GGUF
This model was converted to GGUF format from [`SicariusSicariiStuff/Impish_Mind_8B`](https://huggingface.co/SicariusSicariiStuff/Impish_Mind_8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/SicariusSicariiStuff/Impish_Mind_8B) for more details on the model.

---
Model details:
-
"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..."

    Intended use: Role-Play, Creative Writing, General Tasks.

    Censorship level: Medium - Low

    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:
-
Midnight Enigma

min_p

Divine Intellect

simple-1

Support
-
GPUs too expensive

    My Ko-fi page ALL donations will go for research resources and compute, every bit is appreciated 🙏🏻

Benchmarks
-
SOON

Other stuff
-
    Blog and updates Some updates, some rambles, sort of a mix between a diary and a blog.
    SLOP_Detector Nuke GPTisms, with SLOP detector.
    LLAMA-3_8B_Unaligned The grand project that started it all.

---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo Triangle104/Impish_Mind_8B-Q5_K_S-GGUF --hf-file impish_mind_8b-q5_k_s.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/Impish_Mind_8B-Q5_K_S-GGUF --hf-file impish_mind_8b-q5_k_s.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Impish_Mind_8B-Q5_K_S-GGUF --hf-file impish_mind_8b-q5_k_s.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/Impish_Mind_8B-Q5_K_S-GGUF --hf-file impish_mind_8b-q5_k_s.gguf -c 2048
```