Closed bryanwong17 closed 8 hours ago
Hi, I was wondering if CONCH can return token embedding similar to how CLIP returns token embeddings using clip_model.token_embedding
token embedding
clip_model.token_embedding
The output I expect is of shape[N, max_tokens, 512], but instead I get [N, 512] when using conch_model.encode_text
[N, max_tokens, 512]
[N, 512]
conch_model.encode_text
Thank you in advance!
Hi, I was wondering if CONCH can return
token embedding
similar to how CLIP returns token embeddings usingclip_model.token_embedding
The output I expect is of shape
[N, max_tokens, 512]
, but instead I get[N, 512]
when usingconch_model.encode_text
Thank you in advance!