Comments (10)
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 :).
from self-rag.
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.
from self-rag.
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 ?
from self-rag.
Definitely not, self rag only provides English data. If you need Chinese training data, you need to go through the train data creation process
from self-rag.
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))
from self-rag.
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,
from self-rag.
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.
from self-rag.
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!
from self-rag.
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?
from self-rag.
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.
from self-rag.
Related Issues (20)
- What does YOUR_INPUT_FILE look like? Can you provide an example? Thanks very much! HOT 1
- Explanation needed for [Continue to Use Evidence] HOT 1
- How can I get initial input file for generator?
- model issues
- Processed Input Dataset and Flan-3B Critic Generated Dataset
- Reproducing Self-RAG
- accuracy metric HOT 3
- About parameter `max_depth` HOT 2
- Doesn't the generator need to call the retriever when training the model?
- The critic model will generate different type of token when I use run_reward_vllm.py to generate tokens HOT 1
- some problem with run_long_form_static.py
- Data formatting to call the retriever
- Question Regarding Formula Error in Your Paper
- FactScore Inference Fails with KeyError: 'original_splitted_sentences'
- Incorrect setup of Learning Rate Scheduler HOT 6
- dependency HOT 1
- torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: -9) local_rank: 0 (pid: 14447) of binary: HOT 2
- CUDA Memory is not enough
- Max_logprobs and logprobs value
- How to curate the preceding sentences? and Can you inform the distribution of IsUse token (1~5)?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from self-rag.