Instructions to use Retreatcost/Shisa-K-sakurization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Retreatcost/Shisa-K-sakurization with Transformers:

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

pipe = pipeline("text-generation", model="Retreatcost/Shisa-K-sakurization")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Retreatcost/Shisa-K-sakurization")
model = AutoModelForCausalLM.from_pretrained("Retreatcost/Shisa-K-sakurization")
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 Retreatcost/Shisa-K-sakurization with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Retreatcost/Shisa-K-sakurization

SGLang

How to use Retreatcost/Shisa-K-sakurization 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 "Retreatcost/Shisa-K-sakurization" \
    --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": "Retreatcost/Shisa-K-sakurization",
		"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 "Retreatcost/Shisa-K-sakurization" \
        --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": "Retreatcost/Shisa-K-sakurization",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Shisa-K-sakurization

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

An experimental merge of LoRa adapter to further boost Shisa-K-12B roleplaying capabilities with essence of PocketDoc/Dans-SakuraKaze-V1.0.0-12b.

Can occasionaly output japanese symbols, potentially mitigated by lowering TOP_P to 90 and increasing MIN_P to 0.1.

Uses ChatML.

Oh, and I am planning to use this model as layer range for next KansenSakura update

Merge Details

Merge Method

This model was merged using the Linear merge method using ./retokenized_SHK as a base.

Models Merged

The following models were included in the merge:

./retokenized_SHK + ./lora_Dans-SakuraKaze-V1.0.0-12b-64d

Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
base_model: ./retokenized_SHK
models:
  - model: ./retokenized_SHK
    parameters: 
      weight: 0.0
  - model: ./retokenized_SHK+./lora_Dans-SakuraKaze-V1.0.0-12b-64d
    parameters: 
      weight: 1.0
dtype: bfloat16
out_dtype: bfloat16
tokenizer_source: Retreatcost/KansenSakura-Radiance-RP-12b