PrunaAI

/

Llama-3-8B-Instruct-Gradient-1048k-GGUF-smashed

like 32

Many llama 3 quantizations were created with a missing pretokenizer, 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: ************************************