vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : (embeddings) using same format for "input" and "content" (#10872)

Browse source 
* server : (embeddings) using same format for "input" and "content"

* fix test case

* handle empty input case

* fix test
This commit is contained in:
Xuan Son Nguyen 2024-12-18 09:55:09 +01:00 • committed by GitHub
parent 6b064c92b4
commit 46828872c3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 47 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/utils.hpp
View file

@ -138,6 +138,7 @@ static llama_tokens tokenize_mixed(const llama_context * ctx, const json & json_
* and multiple prompts (multi-tasks):
* - "prompt": ["string1", "string2"]
* - "prompt": ["string1", [12, 34, 56]]
* - "prompt": [[12, 34, 56], [78, 90, 12]]
* - "prompt": [[12, 34, "string", 56, 78], [12, 34, 56]]
*/
static std::vector<llama_tokens> tokenize_input_prompts(llama_context * ctx, const json & json_prompt, bool add_special, bool parse_special) {