lm-sys / lm-sys/FastChat

Sapce and Newline in same token

Open
#2,768 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

model_id = "lmsys/fastchat-t5-3b-v1.0"
tokenizer = AutoTokenizer.from_pretrained(model_id, legacy=False)
tokenizer.encode(' ') == tokenizer.encode('\n')
>>> True

I've seen space and newline in 'added_tokens.json',
they should be 32106 and 32103 separatly.

But in my code, they are the same token.

I'm wondering why.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the Python tokenizer snippet with model_id lmsys/fastchat-t5-3b-v1.0, then compare the reported token IDs in added_tokens.json with the results of tokenizer.encode for a space and newline. Done means identifying why both inputs produce the same token and documenting or correcting the behavior if the repository supports a fix.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
32/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.