Triangle104/MN-12B-Mimicore-WhiteSnake-Q6_K-GGUF

This model was converted to GGUF format from DoppelReflEx/MN-12B-Mimicore-WhiteSnake 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:

Better version of GreenSnake, not too much different in OpenLLM LeaderBoard scores. Merge with cgato/Nemo-12b-Humanize-KTO-Experimental-Latest so this model could perform 'human response'.

This merge model is a gift for Lunar New Year, haha. Enjoy it.

Good for RP, ERP, Story Telling.

PS: It's don't have cgato/Nemo-12b-Humanize-KTO-Experimental-Latest Tokenization issue.

Update: Still have cgato/Nemo-12b-Humanize-KTO-Experimental-Latest Tokenization issue, but randomly occur in rare rate. If you are experiencing this issue, just press re-generate to reroll other message/response.

    Chat Format? ChatML of course!

Models Merged

The following models were included in the merge:

cgato/Nemo-12b-Humanize-KTO-Experimental-Latest DoppelReflEx/MN-12B-Mimicore-GreenSnake

Configuration

The following YAML configuration was used to produce this model:

models:

• model: cgato/Nemo-12b-Humanize-KTO-Experimental-Latest parameters: density: 0.9 weight: 1
• model: DoppelReflEx/MN-12B-Mimicore-GreenSnake parameters: density: 0.6 weight: 0.8 merge_method: dare_ties base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml tokenizer_source: base

---

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/MN-12B-Mimicore-WhiteSnake-Q6_K-GGUF --hf-file mn-12b-mimicore-whitesnake-q6_k.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/MN-12B-Mimicore-WhiteSnake-Q6_K-GGUF --hf-file mn-12b-mimicore-whitesnake-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/MN-12B-Mimicore-WhiteSnake-Q6_K-GGUF --hf-file mn-12b-mimicore-whitesnake-q6_k.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/MN-12B-Mimicore-WhiteSnake-Q6_K-GGUF --hf-file mn-12b-mimicore-whitesnake-q6_k.gguf -c 2048