Orion-14B-LongChat-bpw600-h6-exl2

<!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable html --> <div align="center"> <img src="./assets/imgs/orion_start.PNG" alt="logo" width="50%" /> </div> <div align="center"> <h1> Orion-14B </h1> </div> <div align="center"> <div align="center"> <b>🌐English</b> | <a href="https://huggingface.co/OrionStarAI/Orion-14B-LongChat/blob/main/README_zh.md" target="_blank">🇨🇳中文</a> | <a href="https://huggingface.co/OrionStarAI/Orion-14B-LongChat/blob/main/README_ja.md" target="_blank">🇯🇵日本語</a> | <a href="https://huggingface.co/OrionStarAI/Orion-14B-LongChat/blob/main/README_ko.md" target="_blank">🇰🇷한국어</a> </div> <h4 align="center"> <p> 🤗 <a href="https://huggingface.co/OrionStarAI" target="_blank">HuggingFace Mainpage</a> | 🤖 <a href="https://modelscope.cn/organization/OrionStarAI" target="_blank">ModelScope Mainpage</a><br>🎬 <a href="https://huggingface.co/spaces/OrionStarAI/Orion-14B-App-Demo" target="_blank">HuggingFace Demo</a> | 🎫 <a href="https://modelscope.cn/studios/OrionStarAI/Orion-14B-App-Demo/summary" target="_blank">ModelScope Demo</a><br>😺 <a href="https://github.com/OrionStarAI/Orion" target="_blank">GitHub</a><br>📖 <a href="https://github.com/OrionStarAI/Orion/blob/master/doc/Orion14B_v3.pdf" target="_blank">Tech Report</a> <p> </h4> </div>

Table of Contents

• 📖 Model Introduction
• 🔗 Model Download
• 🔖 Model Benchmark
• 📊 Model Inference<img src="./assets/imgs/vllm.png" alt="vllm" height="20"/> <img src="./assets/imgs/llama_cpp.png" alt="llamacpp" height="20"/>
• 📜 Declarations & License
• 🥇 Company Introduction

<a name="model-introduction"></a><br>

1. Model Introduction

• Orion-14B series models are open-source multilingual large language models trained from scratch by OrionStarAI. The base model is trained on 2.5T multilingual corpus, including Chinese, English, Japanese, Korean, etc, and it exhibits superior performance in these languages. For details, please refer to tech report.

• The Orion-14B series models exhibit the following features:

  • Among models with 20B-parameter scale level, Orion-14B-Base model shows outstanding performance in comprehensive evaluations.
  • Strong multilingual capabilities, significantly outperforming in Japanese and Korean testsets.
  • The fine-tuned models demonstrate strong adaptability, excelling in human-annotated blind tests.
  • The long-chat version supports extremely long texts, performing exceptionally well at a token length of 200k and can support up to a maximum of 320k.
  • The quantized versions reduce model size by 70%, improve inference speed by 30%, with performance loss less than 1%.

<table style="border-collapse: collapse; width: 100%;"> <tr> <td style="border: none; padding: 10px; box-sizing: border-box;"> <img src="./assets/imgs/opencompass_en.png" alt="opencompass" style="width: 100%; height: auto;"> </td> <td style="border: none; padding: 10px; box-sizing: border-box;"> <img src="./assets/imgs/model_cap_en.png" alt="modelcap" style="width: 100%; height: auto;"> </td> </tr> </table>

• Orion-14B series models including:
  • Orion-14B-Base: A multilingual large language foundational model with 14 billion parameters, pretrained on a diverse dataset of 2.5 trillion tokens.
  • Orion-14B-Chat: A chat-model fine-tuned on a high-quality corpus aims to provide an excellence interactive experience for users in the large model community.
  • Orion-14B-LongChat: The long-context version excels at handling extremely lengthy texts, performing exceptionally well at a token length of 200k and can support up to a maximum of 320k.
  • Orion-14B-Chat-RAG: A chat-model fine-tuned on a custom retrieval augmented generation dataset, achieving superior performance in retrieval augmented generation tasks.
  • Orion-14B-Chat-Plugin: A chat-model specifically tailored for plugin and function calling tasks, ideal for agent-related scenarios where the LLM acts as a plugin and function call system.
  • Orion-14B-Base-Int4: A quantized base model utilizing 4-bit integer weights. It significantly reduces the model size by 70% and increases the inference speed by 30% while incurring a minimal performance loss of only 1%.
  • Orion-14B-Chat-Int4: A quantized chat model utilizing 4-bit integer weights.

<a name="model-download"></a><br>

2. Model Download

Model release and download links are provided in the table below:

<a name="model-benchmark"></a><br>

3. Model Benchmarks

3.1. Base Model Orion-14B-Base Benchmarks

3.1.1. LLM evaluation results on examination and professional knowledge

3.1.2. LLM evaluation results on language understanding and common knowledge

3.1.3. LLM evaluation results of OpenCompass testsets

3.1.4. Comparison of LLM performances on Japanese testsets

3.1.5. Comparison of LLM performances on Korean testsets. n = 0 and n = 5 stand for n-shot prompts used in the evaluation

3.1.6. Multilingual evaluation

3.2. Chat Model Orion-14B-Chat Benchmarks

3.2.1. Chat model subjective evaluation of MTBench

3.2.2. Chat model subjective evaluation of AlignBench

3.3. LongChat Model Orion-14B-LongChat Benchmarks

3.3.1. LongChat evaluation of LongBench

3.4. Chat RAG Model Benchmarks

3.4.1. LLM evaluation results of self-built RAG testsets

3.5. Chat Plugin Model Orion-14B-Chat-Plugin Benchmarks

3.5.1. LLM evaluation results of self-built plugin testsets

3.6. Quantized Model Orion-14B-Base-Int4 Benchmarks

3.6.1. Comparison of before and after quantization

<a name="model-inference"></a><br>

4. Model Inference

Model weights, source code, and configuration needed for inference are published on Hugging Face, and the download link is available in the table at the beginning of this document. We demonstrate various inference methods here, and the program will automatically download the necessary resources from Hugging Face.

4.1. Python Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig

tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/Orion-14B", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-14B", device_map="auto",
                                             torch_dtype=torch.bfloat16, trust_remote_code=True)

model.generation_config = GenerationConfig.from_pretrained("OrionStarAI/Orion-14B")
messages = [{"role": "user", "content": "Hello, what is your name? "}]
response = model.chat(tokenizer, messages, streaming=False)
print(response)

In the above Python code, the model is loaded with device_map='auto' to utilize all available GPUs. To specify the device, you can use something like export CUDA_VISIBLE_DEVICES=0,1 (using GPUs 0 and 1).

4.2. Command Line Tool

CUDA_VISIBLE_DEVICES=0 python cli_demo.py

This command-line tool is designed for chat scenarios, and thus, it does not support calling the base model.

4.3. Direct Script Inference

# base model
CUDA_VISIBLE_DEVICES=0 python demo/text_generation_base.py --model OrionStarAI/Orion-14B --tokenizer OrionStarAI/Orion-14B --prompt hello

# chat model
CUDA_VISIBLE_DEVICES=0 python demo/text_generation.py --model OrionStarAI/Orion-14B-Chat --tokenizer OrionStarAI/Orion-14B-Chat --prompt hi

<a name="vllm"></a><br>

4.4. Inference by vllm

• Project URL<br> https://github.com/vllm-project/vllm

• Pull Request<br> https://github.com/vllm-project/vllm/pull/2539

<a name="llama-cpp"></a><br>

4.5. Inference by llama.cpp

• Project URL<br> https://github.com/ggerganov/llama.cpp

• Pull Request<br> https://github.com/ggerganov/llama.cpp/pull/5118

• How to convert to GGUF model

  python convert-hf-to-gguf.py path/to/Orion-14B-Chat --outfile chat.gguf
  

• How to run generation

  ./main --frequency-penalty 0.5 --frequency-penalty 0.5 --top-k 5 --top-p 0.9 -m chat.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e
  

4.6 Example Output

4.6.1. Casual Chat

User: Hello
Orion-14B: Hello! How can I help you today? If you have any questions or need assistance, feel free to ask.
User: What functions do you have?
Orion-14B: As an AI language model, I have a wide range of functions and capabilities, including but not limited to:
  Answering general knowledge questions: I can provide information on various topics such as history, science, geography, and more.
  Providing definitions and explanations: I can explain complex concepts and provide definitions for words and phrases.
  Assisting with tasks: I can help with simple tasks like setting reminders, converting units of measurement, and even ordering food from restaurants.
  Generating text: I can write short stories, essays, articles, and other types of content based on prompts given to me.
  Translating languages: I can translate text from one language to another.
  Chatting: I can engage in conversation with users and respond to their queries in a conversational manner.
  Summarizing long texts: I can summarize longer texts like articles, books, and research papers.
  Generating random numbers and names: I can generate random numbers within a specified range and also suggest names based on certain criteria.
  Playing games: I can play simple games like Hangman, Trivia, and more.
  Providing recommendations: I can recommend movies, music, books, and other forms of entertainment based on user preferences.
  These are just some of the many functions that I am capable of performing. If you have a specific task in mind, feel free to ask me about it.
User: Tell me a joke.
Orion-14B: Sure, here's a classic one-liner: Why don't scientists trust atoms? Because they make up everything.

4.6.2. Japanese & Korean Chat

User：自己を紹介してください
Orion-14B：こんにちは、私の名前はChatMaxで、OrionStarによって開発されたAIアシスタントです。私はユーザーに正確で、客観的で、有用な回答を提供し、彼らが問題を解決し、情報を取得するのを助けることができます。
User：자기소개를 해주세요.
Orion-14B：안녕하세요, 제 이름은 ChatMax입니다. OrionStar에서 개발한 AI 어시스턴트입니다. 저는 사용자들에게 정확하고 객관적이며 유용한 답변을 제공하여 문제를 해결하고 정보를 얻는 데 도움을 줄 수 있습니다.

<a name="declarations-license"></a><br>

5. Declarations, License

5.1. Declarations

We strongly urge all users not to use the Orion-14B model for any activities that may harm national or social security or violate the law. Additionally, we request users not to use the Orion-14B model for internet services without proper security review and filing. We hope all users abide by this principle to ensure that technological development takes place in a regulated and legal environment. We have done our best to ensure the compliance of the data used in the model training process. However, despite our significant efforts, unforeseen issues may still arise due to the complexity of the model and data. Therefore, if any problems arise due to the use of the Orion-14B open-source model, including but not limited to data security issues, public opinion risks, or any risks and issues arising from the model being misled, abused, disseminated, or improperly utilized, we will not assume any responsibility.

5.2. License

Community use of the Orion-14B series models

• For code, please comply with Apache License Version 2.0<br>
• For model, please comply with 【Orion-14B Series】 Models Community License Agreement

<a name="company-introduction"></a><br>

6. Company Introduction

OrionStar is a leading global service robot solutions company, founded in September 2016. OrionStar is dedicated to using artificial intelligence technology to create the next generation of revolutionary robots, allowing people to break free from repetitive physical labor and making human work and life more intelligent and enjoyable. Through technology, OrionStar aims to make society and the world a better place.

OrionStar possesses fully self-developed end-to-end artificial intelligence technologies, such as voice interaction and visual navigation. It integrates product development capabilities and technological application capabilities. Based on the Orion robotic arm platform, it has launched products such as OrionStar AI Robot Greeting, AI Robot Greeting Mini, Lucki, Coffee Master, and established the open platform OrionOS for Orion robots. Following the philosophy of "Born for Truly Useful Robots", OrionStar empowers more people through AI technology.

The core strengths of OrionStar lies in possessing end-to-end AI application capabilities, including big data preprocessing, large model pretraining, fine-tuning, prompt engineering, agent, etc. With comprehensive end-to-end model training capabilities, including systematic data processing workflows and the parallel model training capability of hundreds of GPUs, it has been successfully applied in various industry scenarios such as government affairs, cloud services, international e-commerce, and fast-moving consumer goods.

Companies with demands for deploying large-scale model applications are welcome to contact us.<br> Enquiry Hotline: 400-898-7779<br> E-mail: [email protected]

<div align="center"> <img src="./assets/imgs/wechat_group.jpg" alt="wechat" width="40%" /> </div>