metadata

license: apache-2.0
language:
  - en
  - ja
tags:
  - finetuned
library_name: transformers
pipeline_tag: text-generation

Our Models

This is a prototype of Vecteus-v1

Model Card for VecTeus-Poet

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.

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([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.