prometheusAIR/Ling-3.0-flash-GGUF
Delete Ling-3.0-flash-Q8_0-00004-of-00004.gguf
Delete Ling-3.0-flash-Q8_0-00003-of-00004.gguf
Delete Ling-3.0-flash-Q8_0-00002-of-00004.gguf
Delete Ling-3.0-flash-Q8_0-00001-of-00004.gguf
drop bailing-hybrid patch: superseded by upstream #26608
bailingmoe3 migration: README.md
bailingmoe3 migration: Ling-3.0-flash-Q5_K_XL-00001-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_M-00001-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_M-00002-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_XXL-00001-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_XL-00002-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q4_K_M-00001-of-00002.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_XXL-00002-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q8_0-00001-of-00004.gguf
bailingmoe3 migration: Ling-3.0-flash-Q4_K_M-00002-of-00002.gguf
Update README.md
bailingmoe3 migration: Ling-3.0-flash-Q5_K_XXL-00003-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_XL-00003-of-00003.gguf
bailingmoe3 migration: Ling-3.0-flash-Q5_K_M-00003-of-00003.gguf
Update README.md
Add Q5_K_XXL; consolidate model card
add Ling-3.0-flash-Q5_K_XXL-00003-of-00003.gguf
add Ling-3.0-flash-Q5_K_XXL-00002-of-00003.gguf
add Ling-3.0-flash-Q5_K_XXL-00001-of-00003.gguf
Add Q5_K_XL, KLD measurements, and upstream arch-name notice
add Ling-3.0-flash-Q5_K_XL-00003-of-00003.gguf
add Ling-3.0-flash-Q5_K_XL-00002-of-00003.gguf
add Ling-3.0-flash-Q5_K_XL-00001-of-00003.gguf
Update README.md
Update README.md
Update README.md
card: all 3 quants, 256K context explained, hardware-agnostic default config
context_length 131072 -> 262144 (verified needle-exact to 247K)
context_length 131072 -> 262144 (verified needle-exact to 247K)
context_length 131072 -> 262144 (verified needle-exact to 247K)
add README.md
add Ling-3.0-flash-Q4_K_M-00002-of-00002.gguf
add Ling-3.0-flash-Q4_K_M-00001-of-00002.gguf
add Ling-3.0-flash-Q5_K_M-00003-of-00003.gguf
add Ling-3.0-flash-Q5_K_M-00002-of-00003.gguf
add Ling-3.0-flash-Q5_K_M-00001-of-00003.gguf
add Ling-3.0-flash-Q8_0-00004-of-00004.gguf
add Ling-3.0-flash-Q8_0-00003-of-00004.gguf
add Ling-3.0-flash-Q8_0-00002-of-00004.gguf
patch: rebase onto upstream master 6ea215d17, verified clean apply + build
patch: rebase onto upstream master 6ea215d17, verified clean apply + build
add Ling-3.0-flash-Q8_0-00001-of-00004.gguf
add bailing-hybrid-llama.cpp.patch
add README.md
initial commit
