Instructions to use Ateron/Lotus-Magpic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ateron/Lotus-Magpic with Transformers:

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

pipe = pipeline("text-generation", model="Ateron/Lotus-Magpic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ateron/Lotus-Magpic")
model = AutoModelForCausalLM.from_pretrained("Ateron/Lotus-Magpic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ateron/Lotus-Magpic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ateron/Lotus-Magpic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ateron/Lotus-Magpic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ateron/Lotus-Magpic

SGLang

How to use Ateron/Lotus-Magpic 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 "Ateron/Lotus-Magpic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ateron/Lotus-Magpic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Ateron/Lotus-Magpic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ateron/Lotus-Magpic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Lotus-Magpic

Another merge that seems promising to me. My goal was to create an RP model with natural flow.

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

MN-Violet-Lotus-12B
Magnum-Picaro-0.7-v2-12b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Magnum-Picaro-0.7-v2-12b
    parameters:
      weight: 0.4
  - model: MN-Violet-Lotus-12B
    parameters:
      weight: 0.6
merge_method: linear
dtype: float16

Downloads last month: 5

Safetensors

Model size

12B params

Tensor type

F16

Model tree for Ateron/Lotus-Magpic

Base model

FallenMerick/MN-Violet-Lotus-12B

Finetuned

(2)

this model

Quantizations

2 models

Paper for Ateron/Lotus-Magpic

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 8