Quantization made by Richard Erkhov.

Ninja-v1-NSFW-128k - GGUF

Model creator: https://huggingface.co/Local-Novel-LLM-project/
Original model: https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW-128k/

Name	Quant method	Size
Ninja-v1-NSFW-128k.Q2_K.gguf	Q2_K	2.53GB
Ninja-v1-NSFW-128k.Q3_K_S.gguf	Q3_K_S	2.95GB
Ninja-v1-NSFW-128k.Q3_K.gguf	Q3_K	3.28GB
Ninja-v1-NSFW-128k.Q3_K_M.gguf	Q3_K_M	3.28GB
Ninja-v1-NSFW-128k.Q3_K_L.gguf	Q3_K_L	3.56GB
Ninja-v1-NSFW-128k.IQ4_XS.gguf	IQ4_XS	3.67GB
Ninja-v1-NSFW-128k.Q4_0.gguf	Q4_0	3.83GB
Ninja-v1-NSFW-128k.IQ4_NL.gguf	IQ4_NL	3.87GB
Ninja-v1-NSFW-128k.Q4_K_S.gguf	Q4_K_S	3.86GB
Ninja-v1-NSFW-128k.Q4_K.gguf	Q4_K	4.07GB
Ninja-v1-NSFW-128k.Q4_K_M.gguf	Q4_K_M	4.07GB
Ninja-v1-NSFW-128k.Q4_1.gguf	Q4_1	4.24GB
Ninja-v1-NSFW-128k.Q5_0.gguf	Q5_0	4.65GB
Ninja-v1-NSFW-128k.Q5_K_S.gguf	Q5_K_S	4.65GB
Ninja-v1-NSFW-128k.Q5_K.gguf	Q5_K	4.78GB
Ninja-v1-NSFW-128k.Q5_K_M.gguf	Q5_K_M	4.78GB
Ninja-v1-NSFW-128k.Q5_1.gguf	Q5_1	5.07GB
Ninja-v1-NSFW-128k.Q6_K.gguf	Q6_K	5.53GB
Ninja-v1-NSFW-128k.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 language: - en - ja tags: - finetuned - not-for-all-audiences library_name: transformers pipeline_tag: text-generation

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.