Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q6_K-GGUF

This model was converted to GGUF format from nbeerbower/Hermes2-Gutenberg2-Mistral-7B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Model details:

Hermes2-Gutenberg2-Mistral-7B

NousResearch/Hermes-2-Pro-Mistral-7B finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo. Method

ORPO tuned with 2x RTX 3090 for 3 epochs. Open LLM Leaderboard Evaluation Results

Detailed results can be found here Metric Value Avg. 19.35 IFEval (0-Shot) 37.21 BBH (3-Shot) 28.91 MATH Lvl 5 (4-Shot) 5.66 GPQA (0-shot) 5.26 MuSR (0-shot) 16.92 MMLU-PRO (5-shot) 22.14

---

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/Hermes2-Gutenberg2-Mistral-7B-Q6_K-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q6_K-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q6_k.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/Hermes2-Gutenberg2-Mistral-7B-Q6_K-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q6_K-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q6_k.gguf -c 2048