Not-For-All-Audiences

Instructions to use Local-Novel-LLM-project/Ninja-v1-NSFW-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Local-Novel-LLM-project/Ninja-v1-NSFW-128k with Transformers:

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

pipe = pipeline("text-generation", model="Local-Novel-LLM-project/Ninja-v1-NSFW-128k", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Local-Novel-LLM-project/Ninja-v1-NSFW-128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Local-Novel-LLM-project/Ninja-v1-NSFW-128k", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Local-Novel-LLM-project/Ninja-v1-NSFW-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Local-Novel-LLM-project/Ninja-v1-NSFW-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Local-Novel-LLM-project/Ninja-v1-NSFW-128k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Local-Novel-LLM-project/Ninja-v1-NSFW-128k

SGLang

How to use Local-Novel-LLM-project/Ninja-v1-NSFW-128k 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 "Local-Novel-LLM-project/Ninja-v1-NSFW-128k" \
    --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": "Local-Novel-LLM-project/Ninja-v1-NSFW-128k",
		"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 "Local-Novel-LLM-project/Ninja-v1-NSFW-128k" \
        --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": "Local-Novel-LLM-project/Ninja-v1-NSFW-128k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Local-Novel-LLM-project/Ninja-v1-NSFW-128k with Docker Model Runner:
```
docker model run hf.co/Local-Novel-LLM-project/Ninja-v1-NSFW-128k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Our Models

Model Card for Ninja-v1-NSFW-128k

The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1

Ninja-NSFW-128k has the following changes compared to Mistral-7B-v0.1.

128k context window (8k context in v0.1)
Achieving both high quality Japanese and English generation
Memory ability that does not forget even after long-context generation
Can be generated NSFW

This model was created with the help of GPUs from the first LocalAI hackathon.

We would like to take this opportunity to thank

List of Creation Methods

Chatvector for multiple models
Simple linear merging of result models
Domain and Sentence Enhancement with LORA
Context expansion

Instruction format

Ninja adopts the prompt format from Vicuna and supports multi-turn conversation. The prompt should be as following:

USER: Hi ASSISTANT: Hello.</s>
USER: Who are you?
ASSISTANT: I am ninja.</s>

Example prompts to improve (Japanese)

BAD:　あなたは○○として振る舞います
GOOD: あなたは○○です
BAD: あなたは○○ができます
GOOD: あなたは○○をします

Performing inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Local-Novel-LLM-project/Ninja-v1-NSFW-128k"
new_tokens = 1024

model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, torch_dtype=torch.float16, attn_implementation="flash_attention_2", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)

system_prompt = "あなたはプロの小説家です。\n小説を書いてください\n-------- "

prompt = input("Enter a prompt: ")
system_prompt += prompt + "\n-------- "
model_inputs = tokenizer([system_prompt], return_tensors="pt").to("cuda")


generated_ids = model.generate(**model_inputs, max_new_tokens=new_tokens, do_sample=True)
print(tokenizer.batch_decode(generated_ids)[0])

Merge recipe

WizardLM2 - mistralai/Mistral-7B-v0.1
NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1
Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b
Elizezen/LewdSniffyOtter-7B - Elizezen/SniffyOtter-7B
NTQAI/chatntq-ja-7b-v1.0

The characteristics of each model are as follows.

WizardLM2: High quality multitasking model
Yarn-Mistral-7b-128k: Mistral model with 128k context window
Antler-7B: Model specialized for novel writing
NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model
Elizezen/LewdSniffyOtter-7B Japanese NSFW specialized model

Other points to keep in mind

The training data may be biased. Be careful with the generated sentences.
Set trust_remote_code to True for context expansion with YaRN.
Memory usage may be large for long inferences.
If possible, we recommend inferring with llamacpp rather than Transformers.

Downloads last month: 61

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Local-Novel-LLM-project/Ninja-v1-NSFW-128k

Quantizations

2 models

Spaces using Local-Novel-LLM-project/Ninja-v1-NSFW-128k 2

Collection including Local-Novel-LLM-project/Ninja-v1-NSFW-128k

Ninja

Collection

6 items • Updated Jul 3, 2024