-
Dear Authors,
Firstly, I would like to appreciate your excellent piece of work. My question extends to the question from the issue named "Segment Pooling Implementation #2 ", I had the same questio…
-
### System Info
- CPU: i9 9900k
- GPU: RTX 4090
- TensorRT-LLM Version: 0.9.0.dev2024022000
- Cuda Version: Cuda 12.3
- Driver Version: 545.29.06
- OS: Arch Linux, kernel version 6.7.5
### …
-
作者您好，我在跑您的代码现在主要遇到两个问题。一个就是这个训练得训练多少轮？另一个是训练得到的文件model_bert-dev=**0.xx**for_test_speed.pt是不是和Inference once finished training的代码有关？
我训练了一个晚上发现model_bert-dev=**0.78**for_test_speed.pt，然后用最后Inference o…
-
Cool package.
Wanted to try this with better and newer models
-
어느 정도 공부했다고 판단해서 `OMS`의 `Fun_Info`와 `CodeBert`의 임베딩 정보를 연결해보려고 태스트했다.
이제 대체로 이해는 되는거 같은대 배치는 라이브러리에 맡기는거보다 직접 해주는게 좋을 것 같다.
[A1, A2, A3, ... B1, B2, B3 ... C1, C2, C3 ...] 와 같은 데이터 셋에서 A~D로 대충 배치가…
-
Hello,
I am very interested in your research and am currently trying to run some experiments based on it. However, I encountered an issue while running the program from the HuggingFace_EncDec directo…
-
def init_tokenizer():
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
tokenizer.add_special_tokens({'bos_token': '[DEC]'})
tokenizer.add_special_tokens({'additional_speci…
-
为什么我运行那个安装mcan,py文件有报错。有人可以解答我的疑问吗。谢谢
View detailed results here: C:/Users/qgxiao/ray_results/twitter-experiment
2024-11-10 22:55:22,356 WARNING trial.py:648 -- The path to the trial log directory i…
-
### Feature request
I would like to request that BetterTransformer not be deprecated.
### Motivation
I have come to rely on BetterTransformer significantly for accelerating RoBERTa and BERT models.…
-
## Objective
Currently the classification for non-agri queries is lenient. A lot of queries that are non-agri are being classified as agri and the bot starts responding. We need to train our BERT cla…