Albert Yu
MRU4913
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive:fp8 thx new activity 3 days ago
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled:image support? new activity 4 days ago
llmfan46/Qwen3.5-27B-heretic-v2:fp8 version thxOrganizations
image support?
1
#36 opened 3 days ago
by
MRU4913
fp8 version thx
2
#6 opened 11 days ago
by
MRU4913
Do you train this on your own?
1
#1 opened 12 days ago
by
MRU4913
ltxav_te() got an unexpected keyword argument 'llama_quantization_metadata'
#49 opened about 1 month ago
by
MRU4913
ltxav_te() got an unexpected keyword argument 'llama_quantization_metadata'
1
#79 opened about 1 month ago
by
MRU4913
Share tool parser / thinking parser for VLLM?
#8 opened about 1 month ago
by
MRU4913
Which RL is used by command- a?
2
#3 opened 6 months ago
by
MRU4913
reasoning on / off ?
2
#5 opened 2 months ago
by
TahirC
4bit plz
1
#1 opened 2 months ago
by
MRU4913
Do you have any plan to quantize such models to fp8/nvfp4?
🔥 1
2
#4 opened 4 months ago
by
luoxiao9231
Update chat_template.jinja
2
#4 opened 4 months ago
by
alexrs
Incredible work, and just a few questions!
2
#6 opened 6 months ago
by
MRU4913
Enable thinking not works as expected while using VLLM
1
#16 opened 6 months ago
by
MRU4913
Does VLLM support this model?
👍 3
1
#2 opened 7 months ago
by
MRU4913
Just admit you train on the benchmark datasets
👍👀 18
8
#7 opened 8 months ago
by
ChuckMcSneed
Reproduce this work
4
#3 opened 9 months ago
by
MRU4913
Generation parameters
2
#15 opened 10 months ago
by
MRU4913
Release bases of deprecated models
👍 5
2
#8 opened about 1 year ago
by
ChuckMcSneed