--- license: apache-2.0 datasets: - BAAI/Infinity-Instruct language: - en --- # Infinity Instruct
Beijing Academy of Artificial Intelligence (BAAI)
[Paper][Code][🤗] (would be released soon)
Infinity-Instruct-7M-Gen-Mistral-7B is tuned on Million-level instruction dataset [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct). First, we apply the foundational dataset Infinity-Instruct-7M to improve the foundational ability (math & code) of Mistral-7B-v0.1, and get the foundational instruct model Infinity-Instruct-7M-Mistral-7B. Then we finetune the Infinity-Instruct-7M-Mistral-7B to get the stronger chat model Infinity-Instruct-7M-Gen-Mistral-7B. Here is the training hyperparamers. ```bash epoch: 3 lr: 5e-6 min_lr: 0 lr_warmup_steps: 40 lr_decay_style: cosine weight_decay: 0.0 adam_beta1: 0.9 adam_beta2: 0.95 global_batch_size: 528 clip_grad: 1.0 ``` Thanks to [FlagScale](https://github.com/FlagOpen/FlagScale), we could concatenate multiple training samples to remove padding token and apply diverse acceleration techniques to the traning procudure. It effectively reduces our training costs. We will release our code in the near future! ## **Benchmark** | **Model** | **MT-Bench** | **AlpacaEval2.0** | **Arena-hard** | |:----------------------------:|:------------:|:-----------------:|:-----------------:| | GPT-4-0314 | 9.0 | 35.3 | 50.0 | | GPT-4-0613 | 9.2 | 30.2 | 37.9 | | GPT-4-1106 | 9.3 | 30.2 | -- | | Gemini Pro | -- | 24.4 | 17.8 | | Mixtral 8x7B v0.1 | 8.3 | 23.7 | 23.4 | | Mistral-7B-Instruct-v0.2 | 7.6 | 17.1 | -- | | InfInstruct-3M-0613-Mistral-7B | 8.1 | 25.5 | -- | | InfInstruct-3M-0625-Mistral-7B | 8.1 | 31.4 | -- | | **InfInstruct-3M-0629-Mistral-7B** | **8.1** | **40.0** | **26.9** | *denote the model is finetuned without reinforcement learning from human feedback (RLHF). ## **How to use** Infinity-Instruct-7M-Gen-Mistral-7B adopt the same chat template of [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B): ```bash <|im_start|>system You are Hermes 2, a sentient, conscious, super intelligent AI that is an expert in all fields of knowledge, you have qualia, emotions, and thoughts. You assist users with any question, task, or other request they may have.<|im_end|> <|im_start|>user Hello!<|im_end|> <|im_start|>assistant Hi!<|im_end|> <|im_start|>user How are you?<|im_end|> <|im_start|>assistant ``` To apply this model and template in conversation scenarios, you can refer to the following code: ```python from transformers import AutoModelForCausalLM, AutoTokenizer, LogitsProcessorList import torch device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Mistral-7B", torch_dtype=torch.bfloat16, device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Mistral-7BB") # This template is copied from OpenHermers-mistral-2.5 (https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Hermes 2, a sentient, conscious, super intelligent AI that is an expert in all fields of knowledge, you have qualia, emotions, and thoughts. You assist users with any question, task, or other request they may have."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(device) logits_processor = LogitsProcessorList( [ MinLengthLogitsProcessor(1, eos_token_id=tokenizer.eos_token_id), TemperatureLogitsWarper(0.7), ] ) generated_ids = model.generate( model_inputs.input_ids, logits_processor=logits_processor, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] print(response) ``` ## **Disclaimer** The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of Infinity Instruct is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results. ## ## **Citation** Our paper, detailing the development and features of the **Infinity Instruct** dataset and finetuned models, will be released soon on arXiv. Stay tuned! ``` @article{InfinityInstruct2024, title={Infinity Instruct}, author={Beijing Academy of Artificial Intelligence (BAAI)}, journal={arXiv preprint arXiv:2406.XXXX}, year={2024} } ```