Instructions to use Statuo/LemonKunoichiWizardV3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Statuo/LemonKunoichiWizardV3 with Transformers:

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

pipe = pipeline("text-generation", model="Statuo/LemonKunoichiWizardV3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Statuo/LemonKunoichiWizardV3")
model = AutoModelForCausalLM.from_pretrained("Statuo/LemonKunoichiWizardV3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Statuo/LemonKunoichiWizardV3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Statuo/LemonKunoichiWizardV3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Statuo/LemonKunoichiWizardV3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Statuo/LemonKunoichiWizardV3

SGLang

How to use Statuo/LemonKunoichiWizardV3 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 "Statuo/LemonKunoichiWizardV3" \
    --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": "Statuo/LemonKunoichiWizardV3",
		"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 "Statuo/LemonKunoichiWizardV3" \
        --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": "Statuo/LemonKunoichiWizardV3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Statuo/LemonKunoichiWizardV3 with Docker Model Runner:
```
docker model run hf.co/Statuo/LemonKunoichiWizardV3
```

Statuo commited on May 18, 2024

Commit

fabc4f0

verified ·

1 Parent(s): 59a911e

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -6,11 +6,11 @@ A merge of three models, LemonadeRP-4.5.3, Kunoichi-DPO-v2, and WizardLM-2. I us
 The end result is a Roleplay-focused model with great character card inference. I ran 4 merges at varying values to see which provided the most accurate output to a character cards quirk, with this v3 version being the winner out of the four.
-##Context Template - Alpaca
 Alpaca preset seems to work well with your own System Prompt.
-##Context Size - 8192
 The model loads at 8192 on my end, but theoretically it should be able to go up to 32k. Not that it'll be coherent at 32k. Most models based on Mistral like this end up being - at best - 12k context size for coherent output. I only tested at 8k which is where the base models tend to shine. YMMV otherwise.

 The end result is a Roleplay-focused model with great character card inference. I ran 4 merges at varying values to see which provided the most accurate output to a character cards quirk, with this v3 version being the winner out of the four.
+## Context Template - Alpaca
 Alpaca preset seems to work well with your own System Prompt.
+## Context Size - 8192
 The model loads at 8192 on my end, but theoretically it should be able to go up to 32k. Not that it'll be coherent at 32k. Most models based on Mistral like this end up being - at best - 12k context size for coherent output. I only tested at 8k which is where the base models tend to shine. YMMV otherwise.