Aflah

Results 28 issues of Aflah

I'm interested in contributing scripts which allow users to incorporate data augmentation techniques directly without using external libraries. I can start with stuff like synonym replacement, random insertion, random swap,...

type:feature

NLP Papers often compare against baselines and having a prebuilt random encoder could help with that. A random encoder is similar to a simple encoder with a slight difference here...

Added Help

While running Delete_Retrieve_Generate_Data_Preparation I notice that there is no such file as sentiment_test.txt in the processed_files_with_bert_with_best_head folder and I'm not sure which step generates it as I tried searching and...

Hey! I was trying to run the OpenAI_GPT_Pred and I get this error at one of the steps: ``` --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in ----> 1 op=preditction_with_beam_search("...

Hey! Great paper Can you provide some instructions on running the experiments with custom data? Right now the classifiers etc. are downloaded and not trained is there a way to...

I was trying the following code sample (adapted from the discussion in https://github.com/sgl-project/sglang/issues/81) - ``` import sglang as sgl from sglang import function, gen, set_default_backend, Runtime @sgl.function def tool_use(s, question):...

Hi Thanks for the great library I have a usecase which I think will benefit a lot from Radix Attention. I need to obtain log probs for around a 100K...

There is no num_ctas argument inside the `_layer_norm_fwd_fused` and `_layer_norm_bwd_dwdb` function but it is still being passed which causes errors - ``` --------------------------------------------------------------------------- TypeError Traceback (most recent call last) [](https://localhost:8080/#)...

Hey! Great work Is the code used to generate the plots in Figure 2 publicly available? I would like to reproduce some experiments and that would be really helpful. I...