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

beecf06

verified ·

1 Parent(s): 714506a

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -1

README.md CHANGED Viewed

@@ -1,7 +1,14 @@
 # Lemon Kunoichi Wizard - 7b
 ![LemonKunoichiWizard](https://files.catbox.moe/eivabp.png)
 A merge of three models, LemonadeRP-4.5.3, Kunoichi-DPO-v2, and WizardLM-2. I used Lemonade as a base with Kunoichi being the second biggest influence and WizardLM-2 for logic capabilities.
 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.
@@ -59,4 +66,4 @@ models:
       weight: 0.6
 merge_method: linear
 dtype: float16
-```

+---
+{}
+---
 # Lemon Kunoichi Wizard - 7b
 ![LemonKunoichiWizard](https://files.catbox.moe/eivabp.png)
+[Base Model](https://huggingface.co/Statuo/LemonKunoichiWizardV3/), [4bpw](https://huggingface.co/Statuo/LemonKunoichiWizardv3_4bpw), [6bpw](https://huggingface.co/Statuo/LemonKunoichiWizardv3_6bpw), [8bpw](https://huggingface.co/Statuo/LemonKunoichiWizardv3_8bpw)
+The Quanted versions come with the measurement files in case you want to do your own quants.
 A merge of three models, LemonadeRP-4.5.3, Kunoichi-DPO-v2, and WizardLM-2. I used Lemonade as a base with Kunoichi being the second biggest influence and WizardLM-2 for logic capabilities.
 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.
       weight: 0.6
 merge_method: linear
 dtype: float16
+```