Instructions to use Nohobby/MS-Schisandra-22B-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nohobby/MS-Schisandra-22B-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="Nohobby/MS-Schisandra-22B-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nohobby/MS-Schisandra-22B-v0.3")
model = AutoModelForCausalLM.from_pretrained("Nohobby/MS-Schisandra-22B-v0.3", device_map="auto")
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 Settings

vLLM

How to use Nohobby/MS-Schisandra-22B-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nohobby/MS-Schisandra-22B-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nohobby/MS-Schisandra-22B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nohobby/MS-Schisandra-22B-v0.3

SGLang

How to use Nohobby/MS-Schisandra-22B-v0.3 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 "Nohobby/MS-Schisandra-22B-v0.3" \
    --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": "Nohobby/MS-Schisandra-22B-v0.3",
		"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 "Nohobby/MS-Schisandra-22B-v0.3" \
        --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": "Nohobby/MS-Schisandra-22B-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nohobby/MS-Schisandra-22B-v0.3 with Docker Model Runner:
```
docker model run hf.co/Nohobby/MS-Schisandra-22B-v0.3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Schisandra

Many thanks to the authors of the models used!

Overview

Main uses: RP

Prompt format: Mistral-V3

At the moment, I'm not entirely sure it's an improvement on v0.2. It may have lost some of the previous version's instruction following, but the writing seems a little more vivid and the swipes are more distinct.

Quants

GGUF

exl2: 5.5bpw

Settings

My SillyTavern preset: https://huggingface.co/Nohobby/MS-Schisandra-22B-v0.3/resolve/main/ST-formatting-Schisandra0.3.json

Merge Details

Merging steps

Karasik-v0.3

models:
  - model: Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: [0.2, 0.3, 0.2, 0.3, 0.2]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
  - model: Mistral-Small-NovusKyver
    parameters:
      weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
      density: [0.6, 0.4, 0.5, 0.4, 0.6]
  - model: MiS-Firefly-v0.2-22B
    parameters:
      weight: [0.208, 0.139, 0.139, 0.139, 0.208]
      density: [0.7]
  - model: magnum-v4-22b
    parameters:
      weight: [0.33]
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
merge_method: della_linear
base_model: Mistral-Small-22B-ArliAI-RPMax-v1.1
parameters:
  epsilon: 0.05
  lambda: 1.05
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
tokenizer_source: base

SchisandraVA3

(Config taken from here)

merge_method: della_linear
dtype: bfloat16
parameters:
  normalize: true
  int8_mask: true
tokenizer_source: base
base_model: Cydonia-22B-v1.3
models:
    - model: Karasik03
      parameters:
        density: 0.55
        weight: 1
    - model: Pantheon-RP-Pure-1.6.2-22b-Small
      parameters:
        density: 0.55
        weight: 1
    - model: ChatWaifu_v2.0_22B
      parameters:
        density: 0.55
        weight: 1
    - model: MS-Meadowlark-Alt-22B
      parameters:
        density: 0.55
        weight: 1
    - model: SorcererLM-22B
      parameters:
        density: 0.55
        weight: 1

Schisandra-v0.3

dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
parameters:
  density: 0.5
base_model: SchisandraVA3
models:
  - model: unsloth/Mistral-Small-Instruct-2409
    parameters:
      weight:
        - filter: v_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: o_proj
          value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
        - filter: up_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - filter: gate_proj
          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
        - filter: down_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - value: 0
  - model: SchisandraVA3
    parameters:
      weight:
        - filter: v_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: o_proj
          value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
        - filter: up_proj
          value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
        - filter: gate_proj
          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
        - filter: down_proj
          value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
        - value: 1