abetlen / abetlen/llama-cpp-python
model.tokenize result is different from tranformers tokenizer result
Open
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 1.4k
- PR merge metrics
- PR metrics pending
Description
model.tokenize result is different from tranformers tokenizer result
using the same mode Qwen1.5-7B
input_ids1 = model.tokenize(prompt.encode("utf-8"))
input_ids2 = tokenizer([prompt], padding=False)["input_ids"]
input_ids1 != input_ids2
Contributor guide
Assessment
This issue has not been assessed yet.