Has this model had it's pre-tokenizer fixed?

#10
by smcleod - opened

Many llama 3 quantizations were created with a missing pre-tokenizer, has this been fixed in these quants?

llm_load_vocab: missing pre-tokenizer type, using: 'default'
llm_load_vocab: ************************************
llm_load_vocab: GENERATION QUALITY WILL BE DEGRADED!
llm_load_vocab: CONSIDER REGENERATING THE MODEL
llm_load_vocab: ************************************

they stated it in the paper
you can also test on the playground

oh wait

smcleod changed discussion status to closed

Sign up or log in to comment