vikotse

New feature: 1. Support to retrieve the number of nodes added in trie. 2. Support to return wordEndIndex of text in matching stage. Update Unit Tests for 1. returning wordEndIndex...

What's the bert_model in glyph_config

3

I am confused that what should I write in "bert_model" item. When I use vocab.txt of bert pretraining model, error occurs. When I use the path of bert pretraining model,...

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 1. 执行`pip install -e .[metrics]`，安装无报错。 2. 执行`CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/lora_single_gpu/llama3_lora_sft.yaml`，报错如下 ``` $ CUDA_VISIBLE_DEVICES=0 llamafactory-cli...

ValueError: All strings must be XML compatible: Unicode or ASCII, no NULL bytes or control characters

1

environment: pdfquery=0.4.3 python=2.7.15 I use pdfquery to load [this pdf](http://www.iachina.cn/IC/tkk/03/62d11c2a-8fd6-4b00-aa55-cf9320cf72ae_TERMS.PDF), and encounter an error. error information as follows: pdf.load() File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/pdfquery/pdfquery.py", line 385, in load self.tree = self.get_tree(*_flatten(page_numbers)) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/pdfquery/pdfquery.py",...

As the title suggests. Thanks for contributing this great tool. And look forward to the python2 version.

bge-reranker-large 及 bge-reranker-v2-m3 的 max_length 应是多少

4

根据模型config文件的max_position_embeddings bge-reranker-large是514，bge-reranker-v2-m3是8194 而根据 https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/llm_reranker#for-normal-reranker-bge-reranker-base--bge-reranker-large--bge-reranker-v2-m3--1 ，此处统一为512 ``` import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-v2-m3') model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-v2-m3') model.eval() pairs = [['what is panda?', 'hi'], ['what is panda?', 'The...

bge-reranker-v2-m3 中文场景的 prompt

1

https://huggingface.co/BAAI/bge-reranker-v2-m3 该模型支持多语言，请问中文场景，是否沿用 ```prompt = "Given a query A and a passage B, determine whether the passage contains an answer to the query by providing a prediction of either 'Yes' or...

AskPDF无法读取pdf内容

13

### 这个问题是否已有issue - [X] 我确认没有已有issue，且已阅读**常见问题** ### 运行环境 - **OS**: macOS 14.0 (23A344) - **Zotero version**: 7.0.7 - **Plugin version**: 1.3.4 ### 当前配置信息 _No response_ ### 问题详情 ### 补充说明 已配置好url和key，稳定复现，没有成功过。