Artigenz

/

Artigenz-Coder-DS-6.7B

like 15

Follow

Artigenz 5

I'm running into a failed assert when using Llama.cpp and the Q6 GGUF quant I created:
GGML_ASSERT: D:\a\LLamaSharp\LLamaSharp\llama.cpp:4443: vocab.id_to_token.size() == vocab.token_to_id.size()

Is there an easy fix like editing the tokenizer.json?