Galactica tokenizer's eos_token_id is not set but it's set in its model config. We account for tokenizer's pad_token_id being none in CausalLM but not for eos_token_id.
File "/opt/conda/lib/python3.10/site-packages/text_generation_server/utils/logits_process.py", line 506, in __call__
mask[:, allowed_tokens] = 0
RuntimeError: Could not infer dtype of NoneType
Hi there!
Galactica tokenizer's
eos_token_id
is not set but it's set in its model config. We account for tokenizer'spad_token_id
being none inCausalLM
but not foreos_token_id
.https://github.com/huggingface/text-generation-inference/blob/2b19d671b4d1020e31276477f278ca87cfa37a3c/server/text_generation_server/models/causal_lm.py#L547-L552
On the other hand, Outline's
RegexFSM
gives EOS as the final instruction which isNone
in our case.This then causes
GrammarLogitProcessor.__call__
to fail upon biasing the logits.https://github.com/huggingface/text-generation-inference/blob/2b19d671b4d1020e31276477f278ca87cfa37a3c/server/text_generation_server/utils/logits_process.py#L501-L503