Triangle104/Skyfall-36B-v2-Q5_K_S-GGUF

This model was converted to GGUF format from TheDrummer/Skyfall-36B-v2 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Skyfall v2 is an upscaled version of Mistral Small 2501 with continued training for creativity and RP.

Supported Chat Templates

Mistral v7 Tekken (highly recommended) Metharme (not recommended) Alpaca (may be interesting, especially for cyoa / story)

Description

Creativity, good writing style, good instruct, chain of thought capability, mathematics understanding, and solid tool use performance... This model is peak! This will be my new daily model over all the 70Bs I have used.

---

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/Skyfall-36B-v2-Q5_K_S-GGUF --hf-file skyfall-36b-v2-q5_k_s.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Skyfall-36B-v2-Q5_K_S-GGUF --hf-file skyfall-36b-v2-q5_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/Skyfall-36B-v2-Q5_K_S-GGUF --hf-file skyfall-36b-v2-q5_k_s.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Skyfall-36B-v2-Q5_K_S-GGUF --hf-file skyfall-36b-v2-q5_k_s.gguf -c 2048