-
### Have you searched for similar requests?
My request is the other side of this coin: https://github.com/SillyTavern/SillyTavern/issues/1862
### Is your feature request related to a problem? If…
-
### What happened?
I ran` ./llama-gbnf-validator mygrammar.txt mytestprogram.txt `and after checking the grammar itself, it started to parse the test file and it went into an infinite loop calling st…
-
Llama.cpp has had support for BNF style grammars for a while, but I don't see how I can use them with these bindings.
Is there a way?
If not, is there a good starting place for hooking them up? …
-
https://discord.com/invite/aYbVKQrV The 12 days of christmas llama.cpp grammar gbnf unhackathon is running, Merry Christmas. Check the readme in branch parser https://github.com/meta-introspector/gbnf…
-
MIT emails and dormspam event data is classified as [medium risk](https://infoprotect.mit.edu/risk-classifications#quicktabs-data_risk_levels=1) information, and sending this information to proprietar…
-
Hello,
This isn't a feature request, but it's the best category I could pick. This is really a question around merging PRs for exposing an existing feature to users of Ollama that are being ignored…
-
Hello!
In the V1.5.0 release of whisper.cpp it was mentioned that GBNF-grammar can be used to constrain the decoder in specific scenarios. ggernganov referred to the implementation of that grammar …
-
I am using the grammar below with [OpenHermes-2.5-Mistral-7B-16k-GGUF](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF).
```
root ::= (object | array) endline?
endline ::= "…
-
**Describe the bug**
If you attempt to load a GBNF grammar file that is invalid syntax, the llama-cpp-python C extension crashes the entire Home Assistant process and must be restarted.
**Expected…
-
Let the client accesses the token map, server gives the full tensor to client and let the client choose the next token, then continues decoding, or rollbacks previous decoding step.
This eliminates…