Gompyn

zzztoj in Techmino

17

how to start: - [ ] an API implementation @mm304321141

all-spin mode

1

Is there any plan to support an all-spin mode, like the one found in tetr.io, or maybe that's just not what you want the bot to do? Just to clarify,...

`PreTrainedTokenizer` (slow) strip tokens that are around `unique_no_split_tokens`

11

### System Info - `transformers` version: 4.24.0 - Platform: Linux-5.4.0-135-generic-x86_64-with-glibc2.31 - Python version: 3.10.8 - Huggingface_hub version: 0.11.1 - PyTorch version (GPU?): 1.13.1 (True) - Tensorflow version (GPU?): not installed...

The repository contains the dataset, the evaluation scripts, and the source code for monitors, but no script to allow easy reproduction of results in the paper. Could you please add...

where can I find `lightllm_constraint_decode_kernel`?

1

The $\text{Pre}^3$ branch (https://github.com/ModelTC/LightLLM/tree/pre3-integrated) requires package `lightllm_constraint_decode_kernel` to run. However, I cannot find this package from the repositories in this organization. Is there any open-source implementation of $\text{Pre}^3$ that is...

Error when handling partial terminal

1

I'm trying to use syncode to generate Java programs, but it fails when given a valid token. I simplify the case in the reproduction code. I use a simple test...

[Suprising behavior] lazy quantifiers are treated the same way as greedy quantifiers

6

I want to use `interegular` for tokenization in a C-like programming language. In particular, I use the regex `\/\*.*?\*\/` to match the block comments. By using `?`, I expect the...