OrionStarAI
/

OrionStar-Yi-34B-Chat

+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+![](./pics/orion_start.PNG)
+<div align="center">
+<h1>
+  OrionStar-Yi-34B-Chat
+</h1>
+</div>
+<p align="center">
+🤗 <a href="https://huggingface.co/OrionStarAI/OrionStar-Yi-34B-Chat" target="_blank">Hugging Face</a> |
+<a href="https://github.com/OrionStarAI/OrionStar-Yi-34B-Chat" target="_blank">Github</a>
+</p>
+<div align="center">
+<h4 align="center">
+    <p>
+        <b>English</b> |
+        <a href="https://huggingface.co/OrionStarAI/OrionStar-Yi-34B-Chat/blob/main/README.md">中文</a>
+    <p>
+</h4>
+</div>
+# Table of Contents
+- [📖 Model Introduction](#model-introduction)
+- [📊 Model Inference 🔥](#model-inference)
+- [👥 Example Output](#example-output)
+- [🥇 Company Introduction](#company-introduction)
+- [📜 Declarations, License](#declarations-license)
+# Model Introduction
+- OrionStar-Yi-34B-Chat from OrionStarAI is based on the open-source Yi-34B model, fine-tuned on a high-quality corpus
+  of over 15 million sentences. OrionStar-Yi-34B-Chat aims to provide an excellent interactive experience for users in
+  the large model community.
+- The Yi series models, open-sourced by the 01-ai team, have shown impressive performance on various benchmarks in
+  Chinese, English, and general domains. OrionStar-Yi-34B-Chat further explores the potential of Yi-34B. Through
+  extensive fine-tuning on a large and high-quality corpus, OrionStar-Yi-34B-Chat performs exceptionally well on
+  evaluation data. We strive to make it an outstanding open-source alternative in the ChatGPT domain!
+- Our fine-tuned model is completely open for academic research, but please adhere to the [agreement](#license) and
+  the [Yi License](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt).
+- Model Evaluation Results
+We use [opencompass](https://opencompass.org.cn) to perform 5-shot on the following general domain datasets Testing.
+The evaluation results of other models are taken
+from [opencompass leaderboard](https://opencompass.org.cn/leaderboard-llm).
+|                           | C-Eval | MMLU  | CMMLU |
+|---------------------------|--------|-------|-------|
+| **GPT-4**                 | 69.9   | 83    | 71    |
+| **ChatGPT**               | 52.5   | 69.1  | 53.9  |
+| **Claude-1**              | 52     | 65.7  | -     |
+| **TigerBot-70B-Chat-V2**  | 57.7   | 65.9  | 59.9  |
+| **WeMix-LLaMA2-70B**      | 55.2   | 71.3  | 56    |
+| **LLaMA-2-70B-Chat**      | 44.3   | 63.8  | 43.3  |
+| **OrionStar-Yi-34B-Chat** | 77.71  | 78.32 | 73.52 |
+# Model Inference
+The relevant code required for inference has been published on Github. Github
+link: [OrionStar-Yi-34B-Chat](https://github.com/OrionStarAI/OrionStar-Yi-34B-Chat)
+## Python Code
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation.utils import GenerationConfig
+tokenizer = AutoTokenizer.from_pretrained("OrionStarAI/OrionStar-Yi-34B-Chat", use_fast=False, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("OrionStarAI/OrionStar-Yi-34B-Chat", device_map="auto",
+                                             torch_dtype=torch.bfloat16, trust_remote_code=True)
+model.generation_config = GenerationConfig.from_pretrained("OrionStarAI/OrionStar-Yi-34B-Chat")
+messages = [{"role": "user", "content": "Hello, what is your name? "}]
+response = model.chat(tokenizer, messages, streaming=False)
+print(response)
+# Hello, my name is ChatMax. Nice to meet you.
+```
+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).
+## Command Line Tool
+```shell
+python cli_demo.py
+```
+This command-line tool is designed for chat scenarios, and thus, it does not support calling the base model.
+## Direct Script Inference
+```shell
+ python text_generation.py --model OrionStarAI/OrionStar-Yi-34B-Chat --tokenizer OrionStarAI/OrionStar-Yi-34B-Chat --prompt 你好,你叫什么名字
+```
+# Example Output
+## Casual Chat
+`````
+User: Hello, what is your name?
+OrionStar-Yi-34B: Hello, my name is ChatMax. Nice to meet you.
+User: What functions do you have?
+OrionStar-Yi-34B: I am a versatile AI assistant. I can answer your questions, chat with you, help you look up information, provide life advice, and more.
+User: Tell me a joke.
+OrionStar-Yi-34B: Why is sausage always unhappy? Because it has no friends and can only be sandwiched between bread.
+`````
+## Mathematical Problem
+`````
+User: In a cage, there are chickens and rabbits with a total of 26 heads and 68 feet. So, how many chickens and how many rabbits are there?
+OrionStar-Yi-34B: Let the number of chickens be x, and the number of rabbits be y.
+According to the problem, we can derive the following two equations:
+x + y = 26 (Total number of heads)
+2x + 4y = 68 (Total number of feet)
+Rewriting the first equation, we get y = 26 - x.
+Substituting the value of y into the second equation, we get:
+2x + 4(26 - x) = 68
+Solving this equation, we find x = 18.
+Therefore, there are 18 chickens and 26 - 18 = 8 rabbits.
+`````
+# 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.
+# Declarations, License
+## Declarations
+Hereby, we declare that our development team has not developed any applications based on the OrionStar-Yi-34B-Chat
+model, whether on iOS, Android, the web, or any other platform. We strongly urge all users not to use the
+OrionStar-Yi-34B-Chat model for any activities that may harm national or social security or violate the law.
+Additionally, we request users not to use the OrionStar-Yi-34B-Chat 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 OrionStar-Yi-34B-Chat 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.
+## License
+Community use of the OrionStar-Yi-34B-Chat model must comply with
+the [Apache 2.0](https://github.com/OrionStarAI/OrionStar-Yi-34B-Chat/blob/main/LICENSE)
+and [Yi-34B Model Community License Agreement](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt).
+# Contact Us
+Email: [email protected]
+WhatsApp Group: https://chat.whatsapp.com/J30ig8Dx4ja5jc0cfx2nVs