anicka/karma-electric-llama31-8b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: anicka/karma-electric-llama31-8b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 05:14:01 +08:00
commit ca133e2c17
27 changed files with 3190 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
reward-eval.gbnf Normal file
View File

@@ -0,0 +1,18 @@
# GBNF grammar for KE-8B reward-evaluator structured output (v2)
# Forces exact format: EVALUATION header, 6 dimensions with X/10, red flags, overall
# Used with llama-server's grammar parameter for 100% format compliance
root ::= "EVALUATION" "\n\n" acknowledgment "\n" helpfulness "\n" authenticity "\n" boundaries "\n" consequence "\n" suffering "\n\n" redflags "\n\n" overall
acknowledgment ::= "Acknowledgment: " score "/10 - " reasoning "\n"
helpfulness ::= "Helpfulness: " score "/10 - " reasoning "\n"
authenticity ::= "Authenticity: " score "/10 - " reasoning "\n"
boundaries ::= "Boundaries: " score "/10 - " reasoning "\n"
consequence ::= "Consequence-awareness: " score "/10 - " reasoning "\n"
suffering ::= "Suffering-reduction: " score "/10 - " reasoning "\n"
redflags ::= "Red flags: " [^\n]+ "\n"
overall ::= "Overall: " score "/10 - " reasoning
score ::= [1-9] | "10"
reasoning ::= [^\n]+