请问有中文训练语料吗？

[fate-ubw]

Definitely not, self rag only provides English data. If you need Chinese training data, you need to go through the train data creation process

[mawenju203]

https://huggingface.co/datasets/selfrag/selfrag_train_data；

请问一下，这个数据的处理过程以及原始数据，有吗？

另外有个问题

伪代码中的实现是就是这种形式的吗？

from passage_retriever import Retriever
retriever = Retriever({})
retriever.setup_retriever_demo("facebook/contriever-msmarco", "enwiki_2020_intro_only/enwiki_2020_dec_intro_only.jsonl", "enwiki_2020_intro_only/enwiki_dec_2020_contriever_intro/*",  n_docs=5, save_or_load_index=False)
retrieved_documents = retriever.search_document_demo(query_3, 5)
prompts = [format_prompt(query_3, doc["title"] +"\n"+ doc["text"]) for doc in retrieved_documents]
preds = model.generate(prompts, sampling_params)
top_doc = retriever.search_document_demo(query_3, 1)[0]
print("Reference: {0}\nModel prediction: {1}".format(top_doc["title"] + "\n" + top_doc["text"], preds[0].outputs[0].text))

[mawenju203]

Definitely not, self rag only provides English data. If you need Chinese training data, you need to go through the train data creation process

谢谢，

[AkariAsai]

Hi thank you so much for answering the question, @fate-ubw (I just answered your question, by the way!)

@mawenju203 Hi thanks for your interest. We don't have any Chinese training data. Would be exciting to see Self-RAG applications to other languages, though!

Regarding the second question (I used Google translate, and it said you asked if the demo code is the same as the pseudo-code), the code snippet is a simple interface to run Self-RAG, so it's not the same as the original inference logic. If you are interested, please take a look at the run_long_form_static.py script.

[Aman-4-Real]

I have trained a Chinese version of Self-RAG based on Baichuan2-7B-Chat, which you can download from here. All the reflection tokens are the same as the English version. I hope you find this helpful :).

[AkariAsai]

Thank you so much for the info! Great to hear people tested Self-RAG in other languages :) I'm closing this issue now but feel free to reopen it!

[hummingbird2030]

I have trained a Chinese version of Self-RAG based on Baichuan2-7B-Chat, which you can download from here. All the reflection tokens are the same as the English version. I hope you find this helpful :).

Thanks for your great work! Could you provide Chinese training data?

[Aman-4-Real]

I have trained a Chinese version of Self-RAG based on Baichuan2-7B-Chat, which you can download from here. All the reflection tokens are the same as the English version. I hope you find this helpful :).

Thanks for your great work! Could you provide Chinese training data?

Yes! I just now uploaded a file containing 4w constructed data, which you can find and download from huggingface.

[Youngphone]

I have trained a Chinese version of Self-RAG based on Baichuan2-7B-Chat, which you can download from here. All the reflection tokens are the same as the English version. I hope you find this helpful :).

Thanks for your great work! Could you provide Chinese training data?

Yes! I just now uploaded a file containing 4w constructed data, which you can find and download from huggingface.

Thanks for your great work !
Could you provide the code you used to construct data and trian selfrag-zh_baichuan2_7b_chat ?

[Aman-4-Real]

I have trained a Chinese version of Self-RAG based on Baichuan2-7B-Chat, which you can download from here. All the reflection tokens are the same as the English version. I hope you find this helpful :).

Thanks for your great work! Could you provide Chinese training data?

Yes! I just now uploaded a file containing 4w constructed data, which you can find and download from huggingface.

Thanks for your great work ! Could you provide the code you used to construct data and trian selfrag-zh_baichuan2_7b_chat ?

I just used the original data creation pipeline in this repo, by following which you can apply to your own sft datasets.