Blazgo
·
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
unsloth/DeepSeek-R1-GGUF:PLEASE make one like this for Maverick (LLaMA 4)
new activity
8 days ago
lmarena-ai/p2l-1.5b-rk-01132025:Update!
new activity
12 days ago
deepseek-ai/DeepSeek-V3-0324:685B? what are extra parameters as compared to 671B
Organizations
Blazgo's activity
PLEASE make one like this for Maverick (LLaMA 4)
7
#50 opened 15 days ago
by
Blazgo

685B? what are extra parameters as compared to 671B
2
#32 opened 29 days ago
by
hankhw
What are the system requirements to train this
3
#1 opened 17 days ago
by
Blazgo

Please make a heavily quantized version like you did with R1
1
#1 opened 15 days ago
by
Blazgo

It's been a wild ride, folks :) (end of the Open LLM Leaderboard)
82
20
#1135 opened about 1 month ago
by
clefourrier

Hardware Requirements to run the original model - 671B params
1
4
#185 opened about 2 months ago
by
EdilCamil

Update app.py to prevent users from running multiple jobs
1
1
#46 opened about 2 months ago
by
Blazgo

feat: Choosable CLI, Custom Output Shard Size, LORA extraction
9
#30 opened 6 months ago
by
djuna

Set factory_reboot to True.
3
#36 opened 3 months ago
by
xi0v

How to access gated model?
2
#45 opened about 2 months ago
by
baebee

Post button doesn't appear.
7
#46 opened about 2 months ago
by
Blazgo

Very high usage?
4
#44 opened about 2 months ago
by
Xiaojian9992024

Do not require reasoning but just the ouput
1
#19 opened about 2 months ago
by
ameyv6
Tired of waiting in queue. How to eval locally?
4
#1103 opened 2 months ago
by
Blazgo

How to use this on custom model?
3
#18 opened 2 months ago
by
Blazgo

Disable Think text
5
#11 opened 3 months ago
by
rjsng0904