Instructions to use kainatq/KingRoleplay_12b_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kainatq/KingRoleplay_12b_v1 with Transformers:

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

pipe = pipeline("text-generation", model="kainatq/KingRoleplay_12b_v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kainatq/KingRoleplay_12b_v1")
model = AutoModelForCausalLM.from_pretrained("kainatq/KingRoleplay_12b_v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kainatq/KingRoleplay_12b_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kainatq/KingRoleplay_12b_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kainatq/KingRoleplay_12b_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kainatq/KingRoleplay_12b_v1

SGLang

How to use kainatq/KingRoleplay_12b_v1 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 "kainatq/KingRoleplay_12b_v1" \
    --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": "kainatq/KingRoleplay_12b_v1",
		"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 "kainatq/KingRoleplay_12b_v1" \
        --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": "kainatq/KingRoleplay_12b_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kainatq/KingRoleplay_12b_v1 with Docker Model Runner:
```
docker model run hf.co/kainatq/KingRoleplay_12b_v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

KingRoleplay_12b_v1

KingRoleplay_12b_v1 is a merge of the following models using mergekit : /dev/shm/KingRoleplay_12b_v1 nothingiisreal/MN-12B-Celeste-V1.9 ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2

🧩 Configuration

# Purpose: Inject Narration and Variety into the Smart Core.
# Note: 'models' list includes the output from Stage 1.
merge_method: dare_ties
base_model: mistralai/Mistral-Nemo-Base-2407
models:
  # The "Smart Core" created in Stage 1 (Weight: 0.75)
  - model: /dev/shm/KingRoleplay_12b_v1
    parameters:
      density: 0.60
      weight: 0.75
  # Active Narration & OOC Steering (Weight: 0.15)
  - model: nothingiisreal/MN-12B-Celeste-V1.9
    parameters:
      density: 0.55
      weight: 0.15
  # Variety & Deduplication (Weight: 0.10)
  - model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
    parameters:
      density: 0.50
      weight: 0.10
parameters:
  int8_mask: true
  normalize: true
  #tokenizer_source: union``` 

## 🔄 Merge Info
- 2-Stage Merge: False
- Stage: 1

Downloads last month: -

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for kainatq/KingRoleplay_12b_v1

ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2

nothingiisreal/MN-12B-Celeste-V1.9

Merge model

this model

Quantizations

3 models