-
## Story Explanation
### User Story
As an aligner, I want numbers separated by punctuation (commas or periods) to be tokenized as one word so that I don't have the option of aligning it incorrec…
-
### Your current environment
4xH100.
### Model Input Dumps
_No response_
### 🐛 Describe the bug
When benchmarking the performance of vllm with `benchmark_serving.py`, it will generate different…
-
Pico8 supports some unusual lua syntax that allows users to save on tokens. In particular, you can call split() on a string without using the parenthesis.
I have a program that throws this error w…
-
Exclude the tokens locked to the zero address in `Drips.sol` when calculating the _circulating supply_.
https://etherscan.io/address/0xd0dd053392db676d57317cd4fe96fc2ccf42d0b4
Call the `splittab…
-
It's desirable to allow other zkapps to read your state without needing a proof (which on L1 might not even be feasible because of account update limits), but setting `access = None` also means your z…
-
**Describe the bug**
Query_input's shape is [batch, pos, n_heads, d_model], and the purpose of the code where the error occurred is to reshape query_input to [batch, pos, n_heads, d_head].
I found t…
-
Look for instances where splitting text with .split(" "), tokenize with nltk instead or figure out how to tokenize with more than whitespace
-
Currently, the groups which the user sees/can access isn't limited to their account. We want to change that by implementing the login functionality on the web client.
- [ ] Make necessary forms/text …
-
The `OIDCAuth` class and group-based features added in 2.3.0 are great!
It would be useful for the `OIDCAuth` class to take a callable that is executed at the end of the `OIDCAuth.callback` method …
-
**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