Hugging Face's logo

Spaces:
ejschwartz
/
aidapal-space
Sleeping

App Files Community
ejschwartz commited on
Commit
129bcf2
·
1 Parent(s): 9f58c2e

README

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -19,4 +19,4 @@ names, when given the output of Hex-Rays decompiler output of a function. More
19
  ## TODO / Issues
20
 
21
  * We currently use `transformers` which de-quantizes the gguf. This is easy but inefficient. Can we use llama.cpp or Ollama with zerogpu?
22
- * Model returns the markdown json prefix often. Is this something I am doing wrong? Currently we remove it in present to enable JSON parsing.
 
19
  ## TODO / Issues
20
 
21
  * We currently use `transformers` which de-quantizes the gguf. This is easy but inefficient. Can we use llama.cpp or Ollama with zerogpu?
22
+ * Model returns the markdown json prefix often. [Is this something I am doing wrong?](https://github.com/atredispartners/aidapal/issues/12) Currently we remove it in present to enable JSON parsing.