Advancing Open-source Language Models with Mixed-Quality Data

👁 OpenChat Logo
Online Demo | 👁 GitHub Logo
GitHub | 👁 ArXiv Logo
Paper | 👁 Discord Logo
Discord

Sponsored by RunPod 👁 RunPod Logo

1. Usage
2. Benchmarks
3. Limitations
4. License
5. Dataset Details
6. Citation
7. Acknowledgements

To use this model, we highly recommend installing the OpenChat package by following the installation guide in our repository and using the OpenChat OpenAI-compatible API server by running the serving command from the table below. The server is optimized for high-throughput deployment using vLLM and can run on a consumer GPU with 24GB RAM. To enable tensor parallelism, append --tensor-parallel-size N to the serving command.

Once started, the server listens at localhost:18888 for requests and is compatible with the OpenAI ChatCompletion API specifications. Please refer to the example request below for reference. Additionally, you can use the OpenChat Web UI for a user-friendly experience.

If you want to deploy the server as an online service, you can use --api-keys sk-KEY1 sk-KEY2 ... to specify allowed API keys and --disable-log-requests --disable-log-stats --log-file openchat.log for logging only to a file. For security purposes, we recommend using an HTTPS gateway in front of the server.

Conversation templates

💡 Default Mode (GPT4 Correct): Best for coding, chat and general tasks

GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:

🧮 Mathematical Reasoning Mode: Tailored for solving math problems

Math Correct User: 10.3 − 7988.8133=<|end_of_turn|>Math Correct Assistant:

⚠️ Notice: Remember to set <|end_of_turn|> as end of generation token.

The default (GPT4 Correct) template is also available as the integrated tokenizer.chat_template, which can be used instead of manually specifying the template:

messages = [
 {"role": "user", "content": "Hello"},
 {"role": "assistant", "content": "Hi"},
 {"role": "user", "content": "How are you today?"}
]
tokens = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]

###Task Description:
An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)"
4. Please do not generate any other opening, closing, and explanations.

###The instruction to evaluate:
{orig_instruction}

###Response to evaluate:
{orig_response}

###Reference Answer (Score 5):
{orig_reference_answer}

###Score Rubrics:
[{orig_criteria}]
Score 1: {orig_score1_description}
Score 2: {orig_score2_description}
Score 3: {orig_score3_description}
Score 4: {orig_score4_description}
Score 5: {orig_score5_description}

###Feedback: 

*: Grok results are reported by X.AI.

⚠️ Note that this model was not explicitly trained in Chinese (only < 0.1% of the data is in Chinese). 请注意本模型没有针对性训练中文（中文数据占比小于0.1%）。

@article{wang2023openchat,
 title={OpenChat: Advancing Open-source Language Models with Mixed-Quality Data},
 author={Wang, Guan and Cheng, Sijie and Zhan, Xianyuan and Li, Xiangang and Song, Sen and Liu, Yang},
 journal={arXiv preprint arXiv:2309.11235},
 year={2023}
}

Base model