Jean-Marc Reynaud
lefromage
·
AI & ML interests
None yet
Recent Activity
new activity
9 days ago
google/gemma-3-27b-it-qat-q4_0-gguf:why is the size bigger than regular Q4_0 quants ?
updated
a model
15 days ago
lefromage/gemma-2-2b-it-Q4_0-GGUF
Organizations
None yet
lefromage's activity
why is the size bigger than regular Q4_0 quants ?
4
#1 opened 9 days ago
by
lefromage
llama.cpp llama-cli cannot load : unknown pre-tokenizer type: 'trillion'
3
#1 opened 17 days ago
by
lefromage
neither llama.cpp nor ollama work with any of those models currently
1
#1 opened 17 days ago
by
lefromage
all the scores are NaN
7
#4 opened 28 days ago
by
lefromage
does not support gemma3
4
#157 opened about 1 month ago
by
lefromage
ggml-org/gguf-my-repo fails to build
2
#153 opened about 1 month ago
by
lefromage