Triangle104/Fiendish_LLAMA_3B-Q4_K_S-GGUF

This model was converted to GGUF format from SicariusSicariiStuff/Fiendish_LLAMA_3B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

When innocence fades, And then goes away— A new fiendish purpose— guides its way.

Once impish, now fiendish, for many to play, Three billion parameters of slop underway…

From an impish design— with a quite wholesome tune, This fiendish bitch, was made just to goon.

TL;DR

Impish_LLAMA_3B's naughty sister. Less wholesome, more edge. NOT better, but different.

Superb Roleplay for a 3B size.

Short length response (1-2 paragraphs, usually 1), CAI style.

Naughty, and more evil that follows instructions well enough, and keeps good formatting.

LOW refusals - Total freedom in RP, can do things other RP models won't, and I'll leave it at that. Low refusals in assistant tasks as well.

VERY good at following the character card. Try the included characters if you're having sub optimal results.

Model Details

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

Censorship level: Medium

4.5 / 10 (10 completely uncensored)

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|>

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Fiendish_LLAMA_3B-Q4_K_S-GGUF --hf-file fiendish_llama_3b-q4_k_s.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Fiendish_LLAMA_3B-Q4_K_S-GGUF --hf-file fiendish_llama_3b-q4_k_s.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps 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/Fiendish_LLAMA_3B-Q4_K_S-GGUF --hf-file fiendish_llama_3b-q4_k_s.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Fiendish_LLAMA_3B-Q4_K_S-GGUF --hf-file fiendish_llama_3b-q4_k_s.gguf -c 2048