Instructions to use FallenMerick/MN-Chunky-Lotus-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FallenMerick/MN-Chunky-Lotus-12B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FallenMerick/MN-Chunky-Lotus-12B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FallenMerick/MN-Chunky-Lotus-12B")
model = AutoModelForCausalLM.from_pretrained("FallenMerick/MN-Chunky-Lotus-12B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FallenMerick/MN-Chunky-Lotus-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FallenMerick/MN-Chunky-Lotus-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FallenMerick/MN-Chunky-Lotus-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FallenMerick/MN-Chunky-Lotus-12B

SGLang

How to use FallenMerick/MN-Chunky-Lotus-12B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FallenMerick/MN-Chunky-Lotus-12B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FallenMerick/MN-Chunky-Lotus-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FallenMerick/MN-Chunky-Lotus-12B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FallenMerick/MN-Chunky-Lotus-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FallenMerick/MN-Chunky-Lotus-12B with Docker Model Runner:
```
docker model run hf.co/FallenMerick/MN-Chunky-Lotus-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MN-Chunky-Lotus-12B

I had originally planned to use this model for future/further merges, but decided to go ahead and release it since it scored rather high on my local EQ Bench testing (79.58 w/ 100% parsed @ 8-bit).
Bear in mind that most models tend to score a bit higher on my own local tests as compared to their posted scores. Still, its the highest score I've personally seen from all the models I've tested.
Its a decent model, with great emotional intelligence and acceptable adherence to various character personalities. It does a good job at roleplaying despite being a bit bland at times.

Overall, I like the way it writes, but it has a few formatting issues that show up from time to time, and it has an uncommon tendency to paste walls of character feelings/intentions at the end of some outputs without any prompting. This is something I hope to correct with future iterations.

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

GGUF quants:

Merge Details

Merge Method

This model was merged using the TIES merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Epiculous/Violet_Twilight-v0.2
    parameters:
      weight: 1.0
      density: 1.0
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
    parameters:
      weight: 1.0
      density: 0.54
  - model: flammenai/Mahou-1.5-mistral-nemo-12B
    parameters:
      weight: 1.0
      density: 0.26
merge_method: ties
base_model: TheDrummer/Rocinante-12B-v1.1
parameters:
  normalize: true
dtype: bfloat16

The idea behind this recipe was to take the long-form writing capabilities of Gutenberg, curtail it a bit with the very short output formatting of Mahou, and use Violet Twilight as an extremely solid roleplaying foundation underneath.
Rocinante is used as the base model in this merge in order to really target the delta weights from Gutenberg, since those seemed to have the highest impact on the resulting EQ of the model.

Special shoutout to @matchaaaaa for helping with testing, and for all the great model recommendations. Also, for just being an all around great person who's really inspired and motivated me to continue merging and working on models.