Triangle104/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-Q8_0-GGUF

This model was converted to GGUF format from DavidAU/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Context : 128k.

Required: Llama 3 Instruct template.

"Dark Reasoning" is a variable control reasoning model that is uncensored and operates at all temps/settings and is for creative uses cases and general usage.

This is version 2, MOE.

This one is... wild - 4 example generations below.

This is the MOE version - 32B (4X8B) - consisting of four 8B models converted to DeepHermes reasoning in a MOE (Mixture of Experts) config which results in a 25B "weight" model, that actually has 32B parameters. All four reasoning models / experts are activated.

This version's "thinking"/"reasoning" has been "darkened" by FOUR source models (see model tree) model's DNA and will also be shorter and more compressed. Additional system prompts below to take this a lot further - a lot darker, a lot more ... evil.

Higher temps will result in deeper, richer "thoughts"... and frankly more interesting ones too.

With the MOE setup, this model's thinking/output is even stronger.

The "thinking/reasoning" tech (for the model at this repo) is from the original Llama 3.1 "DeepHermes" model from NousResearch:

[ https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview ]

This version will retain all the functions and features of the original "DeepHermes" model at about 50%-67% of original reasoning power. Please visit their repo for all information on features, test results and so on.

---

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/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-Q8_0-GGUF --hf-file l3.1-moe-4x8b-dark-reasoning-super-nova-rp-hermes-r1-uncensored-25b-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-Q8_0-GGUF --hf-file l3.1-moe-4x8b-dark-reasoning-super-nova-rp-hermes-r1-uncensored-25b-q8_0.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/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-Q8_0-GGUF --hf-file l3.1-moe-4x8b-dark-reasoning-super-nova-rp-hermes-r1-uncensored-25b-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/L3.1-MOE-4X8B-Dark-Reasoning-Super-Nova-RP-Hermes-R1-Uncensored-25B-Q8_0-GGUF --hf-file l3.1-moe-4x8b-dark-reasoning-super-nova-rp-hermes-r1-uncensored-25b-q8_0.gguf -c 2048