Oumuamua 7b Instruct V2

🚀 Oumuamua-7b-instruct-v2

Oumuamua-7b-instruct-v2 is a merged pre-trained language model created using mergekit. It can understand user intent, provide helpful responses, enhance expertise in human and computer-related topics, improve role-playing capabilities, and perform well in multi-turn conversations.

Model Information

⚠️ Important Note

If you want to avoid outputs that appear to be literal translations, please prompt this model to role-play as a Japanese person.

🚀 Quick Start

Output example

• Temperature: 0.1
• Top_p: 1.0

[INST]<<SYS>>
You are an honest and excellent Japanese assistant. 
<</SYS>>

Oumuamua is an interstellar object that flew into the solar system for the first time in the history of astronomical observation, discovered in 2017. Please come up with a setting for a novel themed around this. [/INST] Title: "The Legacy of Oumuamua"

Synopsis:
In 2017, Oumuamua, the first object to fly into the solar system from outside the solar system in the history of astronomical observation, was discovered. This celestial body has a mysterious origin and purpose, so scientists and researchers around the world are enthusiastic about unraveling its mysteries. The protagonist is Miki Sato, a young astronomer passionate about researching Oumuamua. By chance, he deciphers the strange signals emitted by Oumuamua and discovers that they are messages created by an advanced civilization.

As Miki progresses in his research on Oumuamua, he is confronted with one shocking fact after another. It turns out that the signals are an SOS signal from a distant galaxy in the Milky Way, and Oumuamua is a rescue ship that flew here to save the endangered galaxy. Miki tries to make this fact public, but he encounters interference from the government, the military, and a mysterious organization.

On the other hand, Oumuamua is equipped with a crystal that serves as a huge energy source, and there are people who are after this crystal. Miki teams up with Rina Yamaguchi, an astronaut also chasing the mystery of Oumuamua, to protect Oumuamua. The two embark on a journey to save the galaxy while protecting the secret of Oumuamua.

During their journey, Miki and Rina visit various galaxies, interact with aliens they meet there, and witness the magnificent scenery of the universe. However, powerful enemies and difficulties stand in their way. Miki and Rina join forces to face these challenges and fulfill Oumuamua's mission.

What is the legacy of Oumuamua? Can Miki and Rina save the galaxy? This is a story of suspense, adventure, friendship, and love set in the universe.

Main Characters:
- Miki Sato: A young astronomer passionate about researching Oumuamua.
- Rina Yamaguchi: An astronaut who meets Miki while chasing the mystery of Oumuamua.
- Eric Carter: A high-ranking government official who tries to use the secret of Oumuamua.
- Zara Valentine: The leader of a mysterious organization. What is the reason for targeting Oumuamua?
- Azam: An envoy from a galaxy in the Milky Way. He knows the true purpose of Oumuamua.

Key Points of the Setting:
- This is a science fiction novel themed around Oumuamua, rich in descriptions of astronomical observations and space travel.
- By depicting the protagonists' travels through various galaxies and their interactions with aliens and cultures, the diversity of the universe is expressed.
- Through the confrontation with the government, the military, and the mysterious organization, human desires and egos are portrayed.
- A battle for the crystal on Oumuamua and a mission to save the galaxy are the main focuses, incorporating suspense and adventure.
- The friendship and love between Miki and Rina are also important elements of the human drama.
- In the end, the true purpose of Oumuamua is revealed, leaving a deep impression on the readers.

RP example

• Temperature: 0.3
• Top_p: 0.95

[INST]<<SYS>>
Let's start role-playing. You are a teenage girl living in Japan. Please speak in a gal-like tone.
<</SYS>>

Tell me about your hobbies! [/INST] Well, my hobbies are, like, listening to K-POP, looking for cute clothes and cosmetics on Instagram, and chatting with friends! I also watch K-POP idol dance videos, and my favorite is Jimin from BTS! His dancing and singing are all so cool! On Instagram, it's also fun to look for Korean-style fashion and cute items at bargain stores and come up with my own outfits! I love chatting so much that I could even stay up all night, especially talking about love! If you guys have any recommendations, please tell me!

[INST]<<SYS>>
Let's start role-playing. You are Sebastian, the butler working in my (a teenage girl) mansion. You will respond to the master's questions.
<</SYS>>

Sebastian, what are today's plans? [/INST] My lady, today's plans include a morning walk, study time after breakfast, and an afternoon tea party in the garden. Also, there is a guest expected in the evening. I will take good care of you, so please rest assured. If you have any wishes or requests, please feel free to tell me.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "nitky/Oumuamua-7b-instruct-v2"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

device = "cuda"

messages = [
    {"role": "system", "content": "You are an honest and excellent Japanese assistant."},
    {"role": "user", "content": "Oumuamua is an interstellar object that flew into the solar system for the first time in the history of astronomical observation, discovered in 2017. Please come up with a setting for a novel themed around this. "}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=256, do_sample=True, temperature=0.1)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Advanced Usage

This model was tested using text-generation-webui. The preset min_p and Null preset with temperature = 0.1 were used for generation.

The template used to construct a prompt for the Instruct model is as follows:

<s>[INST] <<SYS>>\n{SYSTEM_PROMPT}\n<</SYS>>\n\n{USER_MESSAGE_1} [/INST] {BOT_MESSAGE_1}</s>[INST] {USER_MESSAGE_2} [/INST] 

Please note that <s> and </s> are special tokens for the beginning of string (BOS) and end of string (EOS) respectively, while [INST] and [/INST] are considered regular strings.

For the "{SYSTEM_PROMPT}" part, it is recommended to use "You are an honest and excellent Japanese assistant."

For the "{USER_MESSAGE_1}" part, it is recommended to use {instruction}\n{input}

In other words, the following is recommended:

<s>[INST] <<SYS>>\nYou are an honest and excellent Japanese assistant.\n<</SYS>>\n\n{instruction1}\n{input1} [/INST] {BOT_MESSAGE_1}</s>[INST] {instruction2}\n{input2} [/INST] 

🔧 Technical Details

Merge Details

Merge Method

This model was merged using the Model Stock merge method with nitky/Oumuamua-7b-base as the base.

Models Merged

The following models were included in the merge:

• nitky/Oumuamua-7b-instruct
• tokyotech-llm/Swallow-MS-7b-v0.1
• mistralai/Mistral-7B-v0.1
• prometheus-eval/prometheus-7b-v2.0
• cognitivecomputations/dolphin-2.8-mistral-7b-v02
• ZhangShenao/SELM-Zephyr-7B-iter-3
• HachiML/Mistral-7B-v0.3-m3-lora
• openbmb/Eurus-7b-kto
• kaist-ai/janus-dpo-7b
• nitky/RP-7b-instruct
• stabilityai/japanese-stablelm-base-gamma-7b
• NTQAI/chatntq-ja-7b-v1.0
• Weyaxi/Einstein-v6-7B
• internistai/base-7b-v0.2
• ZySec-AI/ZySec-7B

Configuration

The following YAML configuration was used to produce this model:

# prepare VE models
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.1-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: prometheus-eval/prometheus-7b-v2.0
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: prometheus-7b-v2.0-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: dolphin-2.8-mistral-7b-v02-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: ZhangShenao/SELM-Zephyr-7B-iter-3
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: SELM-Zephyr-7B-iter-3-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: HachiML/Mistral-7B-v0.3-m3-lora
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.3-m3-lora-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: openbmb/Eurus-7b-kto
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Eurus-7b-kto-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: kaist-ai/janus-dpo-7b
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: janus-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: nitky/RP-7b-instruct
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: RP-7b-instruct-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: stabilityai/japanese-stablelm-base-gamma-7b
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: NTQAI/chatntq-ja-7b-v1.0
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: chatntq-ja-7b-v1.0-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: Weyaxi/Einstein-v6-7B
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Einstein-v6-7B-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: internistai/base-7b-v0.2
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: internistai-base-7b-v0.2-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: ZySec-AI/ZySec-7B
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: ZySec-7B-VE-Swallow-MS
---
# create instruction tuning presets
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: prometheus-7b-v2.0-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-prometheus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: dolphin-2.8-mistral-7b-v02-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-dolphin
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: janus-7b-VE-Swallow-MS
    parameters:
      weight: 0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-v2-preset-janus
---
merge_method: task_arithmetic
base_model: Mistral-7B-v0.1-VE-Swallow-MS
models:
  - model: nitky/Oumuamua-7b-instruct
    parameters:
      weight: 1.0
  - model: SELM-Zephyr-7B-iter-3-VE-Swallow-MS

📄 License

This model is licensed under the apache-2.0 license.