We used weight sharing for the query encoder and passage encoder, so the same model should be applied for both.
Note
! We format the passages similar to DPR, i.e. the title and the text are separated by a
[SEP]
token, but token
type ids are all 0-s.
An example usage:
from transformers import AutoTokenizer, DPRContextEncoder
tokenizer = AutoTokenizer.from_pretrained("tau/spider")
model = DPRContextEncoder.from_pretrained("tau/spider")
input_dict = tokenizer("title", "text", return_tensors="pt")
del input_dict["token_type_ids"]
outputs = model(**input_dict)
Runs of tau spider on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
-7
30-day runs
More Information About spider huggingface.co Model
spider huggingface.co
spider huggingface.co is an AI model on huggingface.co that provides spider's model effect (), which can be used instantly with this tau spider model. huggingface.co supports a free trial of the spider model, and also provides paid use of the spider. Support call spider model through api, including Node.js, Python, http.
spider huggingface.co is an online trial and call api platform, which integrates spider's modeling effects, including api services, and provides a free online trial of spider, you can try spider online for free by clicking the link below.
spider is an open source model from GitHub that offers a free installation service, and any user can find spider on GitHub to install. At the same time, huggingface.co provides the effect of spider install, users can directly use spider installed effect in huggingface.co for debugging and trial. It also supports api for free installation.