uiuc-focal-lab syncode issues

uiuc-focal-lab / syncode

Efficient and general syntactical decoding for Large Language Models

MIT License

198 stars 16 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Local inference for batch size > 1

#127 shubhamugare opened 9 hours ago
0
Constrained decoding causes the LLM to not know when to stop.

#126 ksrinivs64 closed 5 days ago
4
Minor fix

#125 shubhamugare closed 2 weeks ago
0
Support for batched inference?

#124 ksrinivs64 closed 2 weeks ago
4
Refactor evaluation

#123 shubhamugare closed 2 weeks ago
0
Make opp a command-line flag and member of HuggingFaceModel.

#122 pmfirestone closed 3 weeks ago
0
Add opp flag.

#121 pmfirestone closed 3 weeks ago
0
Map syncode version to transformers version

#120 shubhamugare closed 1 month ago
0
Add grammar ambiguity error check

#119 shubhamugare closed 1 month ago
0
Do you support earley parser？

#118 benjamin12342 opened 1 month ago
1
Turn debug flag off

#117 shubhamugare closed 1 month ago
0
Incorrect constrained generation for regex

#116 teoremma closed 1 month ago
4
Skip or speedup lexer preprocessing

#115 teoremma opened 1 month ago
3
Add few more things in SQL grammar

#114 shubhamugare closed 1 month ago
0
Update incrementality handling of the parser

#113 shubhamugare closed 2 months ago
0
Disallow empty generation

#112 shubhamugare closed 2 months ago
0
Add missing features in SQL grammar

#111 shubhamugare closed 2 months ago
0
Fix a lexer issue

#110 shubhamugare closed 2 months ago
0
Fix SQL grammar issues

#109 shubhamugare closed 2 months ago
0
Fix SQL grammar issues

#108 shubhamugare closed 2 months ago
0
Fix SQL grammar issues

#107 shubhamugare closed 2 months ago
0
Fix SQL issues

#106 shubhamugare closed 2 months ago
0
Beam search notebook

#105 shubhamugare closed 3 months ago
0
Beam search issue

#104 HichemAK closed 2 months ago
6
Update JSON eval notebook with original and explicit prompts

#103 shubhamugare closed 3 months ago
0
Remove stale scripts

#102 shubhamugare closed 3 months ago
0
Update README.md

#101 shubhamugare closed 3 months ago
0
Decouple infer and evaluation

#100 shubhamugare closed 3 months ago
0
Update README.md

#99 shubhamugare closed 3 months ago
0
Fix JSON evaluation for gemma

#98 shubhamugare closed 3 months ago
0
Remove python time based logging

#97 shubhamugare closed 3 months ago
0
Some dead code cleanup

#96 shubhamugare closed 3 months ago
0
Add a test for `grammar_strict`

#95 shubhamugare closed 3 months ago
0
Improve precision of `grammar_strict`

#94 shubhamugare closed 3 months ago
0
Make grammar_strict default at all places

#93 shubhamugare closed 3 months ago
0
add cypher support

#92 zdnhub closed 3 months ago
1
Update README.md

#91 shubhamugare closed 4 months ago
0
Update README.md

#90 shubhamugare closed 4 months ago
0
Update README.md

#89 shubhamugare closed 4 months ago
0
Lexer ambiguity docs

#88 shubhamugare closed 4 months ago
0
Add tests for WS and refactor the logic

#87 shubhamugare closed 4 months ago
0
Initial llama.cpp logits processor

#86 tarsur909 opened 4 months ago
0
Update FOL grammar

#85 shubhamugare closed 4 months ago
0
GenerationMixin._get_logits_warper() missing 1 required positional argument: 'device'

#84 XZF0 closed 4 months ago
3
Added timeout for parsing FOL Formula to Tree + Added README for PROVER9 binary

#83 rohangumaste closed 5 months ago
0
SynCode for fill-in-the-middle models

#82 AzizCode92 opened 6 months ago
3
Remove unused code

#81 shubhamugare closed 6 months ago
0
Fix issue with `quantize` parameter

#80 border-b closed 6 months ago
1
Option to add huggingface token for gated models?

#79 border-b closed 6 months ago
2
"Generate Indentation-Error-Free Python Code" example with "microsoft/phi-2" model generates error

#78 border-b closed 6 months ago
12