nsfw

Visual novel

roleplay

mergekit

Merge

conversational

text-generation-inference

Model card Files Files and versions

xet

Community

Instructions to use spow12/ChatWaifu_32B_reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use spow12/ChatWaifu_32B_reasoning with Transformers:

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

pipe = pipeline("text-generation", model="spow12/ChatWaifu_32B_reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("spow12/ChatWaifu_32B_reasoning")
model = AutoModelForCausalLM.from_pretrained("spow12/ChatWaifu_32B_reasoning")
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 spow12/ChatWaifu_32B_reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spow12/ChatWaifu_32B_reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "spow12/ChatWaifu_32B_reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spow12/ChatWaifu_32B_reasoning

SGLang

How to use spow12/ChatWaifu_32B_reasoning 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 "spow12/ChatWaifu_32B_reasoning" \
    --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": "spow12/ChatWaifu_32B_reasoning",
		"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 "spow12/ChatWaifu_32B_reasoning" \
        --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": "spow12/ChatWaifu_32B_reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use spow12/ChatWaifu_32B_reasoning with Docker Model Runner:
```
docker model run hf.co/spow12/ChatWaifu_32B_reasoning
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

Merged model using mergekit

This model aim to make a agent system with keeping given our waifu persona.

Merge Format

models:
    - model: trashpanda-org/QwQ-32B-Snowdrop-v0
    - model: Qwen/QwQ-32B_sft(private)
merge_method: model_stock
base_model: Qwen/QwQ-32B
dtype: bfloat16
tokenizer_source: base

Model Details

Model Description

Developed by: spow12(yw_nam)
Shared by : spow12(yw_nam)
Model type: CausalLM
Language(s) (NLP): japanese, english
Finetuned from model : Qwen/QwQ-32B

Chat Format

<|im_start|>system
This is the system prompt.<|im_end|>
<|im_start|>user
Instructions placed here.<|im_end|>
<|im_start|>assistant
The model's response will be here.<|im_end|>

Reasoning mode

If you want to turn on the reasoning mode, incorporate below sentence in system message or instruction.

Before answer, organize thoughts your thought inside <think> and </think> tags after that, answer in a concise manner.

Dataset

SFT (585K)

Riddle Joker(Prviate)
Café Stella and the Reaper's Butterflies(Private)
Senren＊Banka(Private)
HuggingFaceTB/smoltalk
microsoft/orca-agentinstruct-1M-v1
Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
facebook/natural_reasoning
Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-39.6k-formatted
Aratako/Synthetic-JP-EN-Coding-Dataset-801k
Aratako/Magpie-Tanuki-8B-97k
SkunkworksAI/reasoning-0.01
anthracite-org/stheno-filtered-v1.1
Aratako/Synthetic-JP-EN-Translation-Dataset-Magpie-Nemotron-4-20k
open-r1/OpenR1-Math-220k
Aratako/Synthetic-Japanese-Roleplay-NSFW-Claude-3.5s-15.3k-formatted
Nopm/Opus_WritingStruct
gretelai/synthetic_text_to_sql
kalomaze/Opus_Instruct_3k
PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
SicariusSicariiStuff/Bluemoon_Top50MB_Sorted_Fixed
roleplay4fun/aesir-v1.1
Aratako/Rosebleu-1on1-Dialogues-RP_v2

Use & Credit

This model is currently available for non-commercial & Research purpose only. Also, since I'm not detailed in licensing, I hope you use it responsibly.

By sharing this model, I hope to contribute to the research efforts of our community (the open-source community and Waifu Lovers).

Citation

@misc {ChatWaifu_32B_reasoning,
    author       = { YoungWoo Nam },
    title        = { spow12/ChatWaifu_32B_reasoning },
    year         = 2025,
    url          = { https://huggingface.co/spow12/ChatWaifu_32B_reasoning },
    publisher    = { Hugging Face }
}