lm-sys / lm-sys/FastChat

vicuna-13b-v1.3 padding token maybe wrong ?

Open
#2,076 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

load model https://huggingface.co/lmsys/vicuna-13b-v1.3
pad_token ==

__________________________________________
token class ,tokens vocab :32000
LlamaTokenizerFast(name_or_path='/models/vicuna-13b-v1.3', vocab_size=32000, model_max_length=2048, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=True), 'eos_token': AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=True), 'unk_token': AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=True), 'pad_token': ''}, clean_up_tokenization_spaces=False)
tokenizer.bos_token='' ,bos_token_id=1
tokenizer.eos_token='' ,eos_token_id=2
tokenizer.pad_token='' ,pad_token_id=0
tokenizer.unk_token='' ,unk_token_id=0
tokenizer.all_special_tokens=['', '', '', '']

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

Start with the Vicuna 13B v1.3 model on Hugging Face and inspect its LlamaTokenizerFast configuration, focusing on the reported pad_token and pad_token_id values. Compare the padding configuration with the model's bos, eos, and unk tokens, then verify whether the reported padding assignment is expected or needs correction.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.