Phi 3 4k , 128k mot working
kishoretvk opened this issue · comments
In chat model they error out.
Just confirmed that Phi-3-mini-4k-instruct is working with the latest release version 0.1.3 of SiLLM from pip.
There is an error IndexError: piece id is out of range.
when trying to load the sentencepiece tokenizer for Phi-3 at this point. You can just delete the file tokenizer.model
if you have downloaded tokenizer.json
and tokenizer_config.json
in the model directory.
The 128k version is using a custom scaled rotary embedding that I didn't port to SiLLM yet. Hopefully will have some time to take a look in the next days.
Here's the original source that needs to be ported:
SuScaledRotaryEmbedding
YarnScaledRotaryEmbedding
thanks a lot and for 128k as well same error shows up at 4k one,
one more thing, DPO mistral 7b instruct v2 also give error.
Just confirmed that Phi-3-mini-4k-instruct is working with the latest release version 0.1.3 of SiLLM from pip. There is an error
IndexError: piece id is out of range.
when trying to load the sentencepiece tokenizer for Phi-3 at this point. You can just delete the filetokenizer.model
if you have downloadedtokenizer.json
andtokenizer_config.json
in the model directory.The 128k version is using a custom scaled rotary embedding that I didn't port to SiLLM yet. Hopefully will have some time to take a look in the next days. Here's the original source that needs to be ported: SuScaledRotaryEmbedding YarnScaledRotaryEmbedding
great.
Could you share the error message and a link to the model that doesn't work?