|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
- ja |
|
tags: |
|
- finetuned |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
--- |
|
<img src="./veteus_logo.svg" width="100%" height="20%" alt=""> |
|
|
|
# Our Models |
|
- [Vecteus](https://huggingface.co/Local-Novel-LLM-project/Vecteus-v1) |
|
|
|
- [Ninja-v1](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1) |
|
|
|
- [Ninja-v1-128k](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-128k) |
|
|
|
- [Ninja-v1-NSFW-128k](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW-128k) |
|
|
|
## Model Card for Ninja-v1.0 |
|
|
|
The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1 |
|
|
|
Ninja has the following changes compared to Mistral-7B-v0.1. |
|
- Achieving both high quality Japanese and English generation |
|
- 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 |
|
|
|
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:γγγͺγγ―ββγ¨γγ¦ζ―γθγγΎγ |
|
- GOOD: γγͺγγ―ββγ§γ |
|
|
|
- BAD: γγͺγγ―ββγγ§γγΎγ |
|
- GOOD: γγͺγγ―ββγγγΎγ |
|
|
|
## Performing inference |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model = AutoModelForCausalLM.from_pretrained("Local-Novel-LLM-project/Ninja-v1-128k", trust_remote_code=True) |
|
tokenizer = AutoTokenizer.from_pretrained("Local-Novel-LLM-project/Ninja-v1-128k") |
|
|
|
prompt = "Once upon a time," |
|
input_ids = tokenizer.encode(prompt, return_tensors="pt") |
|
|
|
output = model.generate(input_ids, max_length=100, do_sample=True) |
|
generated_text = tokenizer.decode(output) |
|
|
|
print(generated_text) |
|
```` |
|
|
|
## 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 |
|
- NTQAI/chatntq-ja-7b-v1.0 |
|
|
|
The characteristics of each model are as follows. |
|
|
|
- WizardLM2: High quality multitasking model |
|
- Antler-7B: Model specialized for novel writing |
|
- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model |
|
|
|
## 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. |