Vecteus-v1

<img src="./veteus_logo.svg" width="100%" height="20%" alt="">

Our Models

• Vecteus

• Ninja-v1

• Ninja-v1-NSFW

• Ninja-v1-128k

• Ninja-v1-NSFW-128k

Model Card for VecTeus-v1.0

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

VecTeus 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
• Can be generated NSFW
• Memory ability that does not forget even after long-context generation

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

Freed from templates. Congratulations

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/Vecteus-v1"
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

• VT0.1 = Ninjav1 + Original Lora

• VT0.2 = Ninjav1 128k + Original Lora

• VT0.2on0.1 = VT0.1 + VT0.2

• VT1 = all VT Series + Lora + Ninja 128k and Normal

Other points to keep in mind

• The training data may be biased. Be careful with the generated sentences.
• Memory usage may be large for long inferences.
• If possible, we recommend inferring with llamacpp rather than Transformers.