Instructions to use grimjim/Magnolia-v3-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Magnolia-v3-12B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Magnolia-v3-12B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Magnolia-v3-12B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Magnolia-v3-12B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use grimjim/Magnolia-v3-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Magnolia-v3-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/Magnolia-v3-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimjim/Magnolia-v3-12B

SGLang

How to use grimjim/Magnolia-v3-12B 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 "grimjim/Magnolia-v3-12B" \
    --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": "grimjim/Magnolia-v3-12B",
		"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 "grimjim/Magnolia-v3-12B" \
        --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": "grimjim/Magnolia-v3-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimjim/Magnolia-v3-12B with Docker Model Runner:
```
docker model run hf.co/grimjim/Magnolia-v3-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Magnolia-v3-12B

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

This merge takes advantage of task arithmetic to incorporate the influence of two additional models at low weight in order to improve default creative outputs.

Tested at temperature 1.0 with minP 0.01; that was it. Mistral prompt formats for Nemo should work, although I successfully tested with a variant:

User message prefix: [INST]user
User message suffix: [/INST]
Assistant message prefix: [INST]assistant
Assistant message suffix: [/INST]

Testing with a blank sysprompt was not awful, though a good sysprompt will elicit more desired behavior.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using grimjim/mistralai-Mistral-Nemo-Base-2407 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: grimjim/mistralai-Mistral-Nemo-Base-2407
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: true
slices:
- sources:
  - layer_range: [0, 40]
    model: grimjim/mistralai-Mistral-Nemo-Base-2407
  - layer_range: [0, 40]
    model: grimjim/mistralai-Mistral-Nemo-Instruct-2407
    parameters:
      weight: 0.9
  - layer_range: [0, 40]
    model: grimjim/magnum-consolidatum-v1-12b
    parameters:
      weight: 0.1
  - layer_range: [0, 40]
    model: grimjim/magnum-twilight-12b
    parameters:
      weight: 0.001
  - layer_range: [0, 40]
    model: TheDrummer/Rocinante-12B-v1.1
    parameters:
      weight: 0.001
  - layer_range: [0, 40]
    model: nbeerbower/Mistral-Nemo-Prism-12B
    parameters:
      weight: 0.05