Triangle104/Prismatic-12b-Q8_0-GGUF

This model was converted to GGUF format from ProdeusUnity/Prismatic-12b 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:

The sparkling courage I longed for, what I got is small... My tears are surely the prism of tomorrow... Say "Hello!" to the ideal future, let's go see them~

Listen to the song on youtube: https://www.youtube.com/watch?v=v3I6EVlyPx4

One off merge for a friend, though it came out rather good, I like it, so try it?

mistralai/Mistral-Nemo-Base-2407 inflatebot/MN-12b-Mag-Mell-R1 nbeerbower/Mistral-Nemo-Prism-12B-v5

License for this model Apache 2.0

Format: Mistral Tekken or ChatML

Thank you to AuriAetherwiing for helping me merge the models and for providing compute (A40).

Details

This is a merge of pre-trained language models created using mergekit. Merge Details Merge Method

This model was merged using the ties merge method using mistralai_Mistral-Nemo-Base-2407 as a base. Models Merged

Models Merged The following models were included in the merge:

/inflatebot_MN-12B-Mag-Mell-R1 /nbeerbower_Mistral-Nemo-Prism-12B-v5 Configuration

The following YAML configuration was used to produce this model:

models:

model: /inflatebot_MN-12B-Mag-Mell-R1 parameters: weight: 0.3 density: 0.5
model: /nbeerbower_Mistral-Nemo-Prism-12B-v5 parameters: weight: 0.4 density: 0.75 base_model: /mistralai_Mistral-Nemo-Base-2407 parameters: epsilon: 0.05 normalize: true lambda: 1 merge_method: ties dtype: bfloat16

---

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/Prismatic-12b-Q8_0-GGUF --hf-file prismatic-12b-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Prismatic-12b-Q8_0-GGUF --hf-file prismatic-12b-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/Prismatic-12b-Q8_0-GGUF --hf-file prismatic-12b-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Prismatic-12b-Q8_0-GGUF --hf-file prismatic-12b-q8_0.gguf -c 2048