-
/home/horanchen/anaconda3/envs/lightrag/bin/python /home/horanchen/ydy/study/code/LightRAG/examples/lightrag_hf_demo.py
INFO:lightrag:Logger initialized for working directory: ./dickens
DEBUG:lightr…
-
**Describe the bug**
Using the OGA tokenizer to encode the wikitext-2-raw-v1 hangs and does not return, but works fine for wikitest-2-v1.
**To Reproduce**
Steps to reproduce the behavior:
import…
WA225 updated
1 month ago
-
### System Info
trl-0.8.6
transformers-4.41.2
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` fold…
-
When I run the ebook on @piscosour, I get: http://pastebin.com/atBRUjR5
```
/task/__gems__/gems/punkt-segmenter-0.9.1/lib/punkt-segmenter/punkt/sentence_tokenizer.rb:81:in `split_in_sentences': undef…
-
Hi, awesome project!
I am experimenting with using "unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit" for inference. I am using 1 A100 GPU with 16 core CPU. However, inference time for one sentence t…
-
**Is your feature request related to a problem? Please describe.**
- As a user, I want to split my documents based on a token limit. I would like to use HuggingFace tokenizers, Sentence Transformers …
-
### 🐛 Describe the bug
I've configured log4j to log using `JsonTemplateLayout`. Below the part of the [original `log4j.xml`](https://github.com/pytorch/serve/blob/master/frontend/server/src/main/reso…
-
Dear experts,
I found there are two pad tokens in deepseek-coder. What's the difference between them?
When I need to use pad token, which one shall I use?
- tokenizer.json
```json
{
"i…
-
你好!!最近复现时对有些细节有些疑问,想请教一些问题~
1.文件夹genresults中的内容是通过文件夹prompts+文件夹questions中的内容产生的嘛,但我看prompt中的格式内容好像又跟genresults中的不太相符,所以想请教一下,如果想从对话生成开始做的话应该怎么开始诶,请问可以提供和api交互的脚本嘛~
2.关于文件夹里rag的内容,没太明白这里的rag内容是怎么进行检…
-
### Feature request
Hi thanks for the library! When using tokenizer, for example, for batch-generation with GPT2 (in https://discuss.huggingface.co/t/batch-generation-with-gpt2/1517), it seems that…