DC
Downtown-Case
AI & ML interests
None yet
Recent Activity
new activity 9 days ago
BigDannyPt/Z-Image-Turbo-GGUF-Collection:What was the command/method used to make these quants? liked a model 9 days ago
gghfez/boring-experiment updated a model about 1 month ago
Downtown-Case/MiMo-V2.5-Dummy-GGUFOrganizations
What was the command/method used to make these quants?
#1 opened 9 days ago
by
Downtown-Case
How, exactly, did you make these?
2
#1 opened about 1 month ago
by
Downtown-Case
KLD Files
1
#13 opened about 1 month ago
by
Downtown-Case
Mainline contribution?
5
#1 opened about 2 months ago
by
NeedAHugNOW
โThe doom lies in yourself, not in your name.โ
๐ 7
500
#15 opened 10 months ago
by
jukofyork
New quants IQ4_XS isn't loaded by llama.cpp(b9050) with segfault issue
12
#8 opened about 2 months ago
by
smalinin
QAT?
#1 opened 3 months ago
by
Downtown-Case
Could you make a smaller quantized model?
3
#1 opened 6 months ago
by
lklklk248
Quantization request.
2
#2 opened 7 months ago
by
daibuzizai
guys we also need some AIR
โโค๏ธ 50
30
#1 opened 9 months ago
by
jacek2024
Thanks for these!
3
#1 opened 8 months ago
by
Downtown-Case
Preservation of rare knowledge
๐ 5
3
#3 opened 8 months ago
by
algorithm
Should ffn_down experts be quantized the same as ffn_up/ffn_gate?
5
#2 opened 9 months ago
by
Downtown-Case
Error tensor 'blk.92.nextn.embed_tokens.weight' not found
17
#1 opened 9 months ago
by
Bikkies
โThe doom lies in yourself, not in your name.โ
๐ 7
500
#15 opened 10 months ago
by
jukofyork
Backend Optimization?
2
#382 opened 9 months ago
by
Downtown-Case
Should ffn_down experts be quantized the same as ffn_up/ffn_gate?
5
#2 opened 9 months ago
by
Downtown-Case
Error tensor 'blk.92.nextn.embed_tokens.weight' not found
17
#1 opened 9 months ago
by
Bikkies
Error tensor 'blk.92.nextn.embed_tokens.weight' not found
17
#1 opened 9 months ago
by
Bikkies
Should ffn_down experts be quantized the same as ffn_up/ffn_gate?
5
#2 opened 9 months ago
by
Downtown-Case