feat: enable GPU acceleration for Bielik GGUF models
7c2f84b
Patryk Studzinski
commited on
Spaces:
Sleeping
Sleeping
Commit History
add GBNF grammar for car advertisement gap filling; update LlamaCppModel to support loading grammar from file
c14ac43
Patryk Studzinski
commited on
add GBNF grammar utilities for structured LLM output; integrate grammar in model generation
329abd1
Patryk Studzinski
commited on
update LlamaCppModel initialization parameters and enable verbose logging for model loading; update llama-cpp-python requirement
fb1531e
Patryk Studzinski
commited on
enhance error handling in LlamaCppModel initialization; include full traceback on failure
cdff838
Patryk Studzinski
commited on
add get_info method to return model details for /models endpoint
baa08b7
Patryk Studzinski
commited on
add debug logging for batch infill and model generation processes; update bielik model configuration
9d2cc15
Patryk Studzinski
commited on
increase context size and improve message handling in LlamaCppModel
db4996d
Patryk Studzinski
commited on
adding-bielik-gguf
8cde7d1
Patryk Studzinski
commited on