rombo dawg
rombodawg
AI & ML interests
My patreon:
https://www.patreon.com/c/Rombodawg
My Twitter:
https://x.com/dudeman6790
Recent Activity
new activity 1 day ago
MiniMaxAI/MiniMax-M2.5:Minimax 2.7??? new activity about 1 month ago
microsoft/Phi-4-reasoning-vision-15B:Typo in model card? commentedon an article about 2 months ago
GGML and llama.cpp join HF to ensure the long-term progress of Local AIOrganizations
Minimax 2.7???
49
#53 opened 20 days ago
by rombodawg
Typo in model card?
2
#2 opened about 1 month ago
by 
J22
Question
8
#1 opened about 2 months ago
by rombodawg
Minimax-m2.5???
3
#2 opened about 2 months ago
by rombodawg
when release model?
8
#1 opened 4 months ago
by 
mxymxymxy
120b next
5
#1 opened 4 months ago
by rombodawg
Extremely misleading benchmarks
➕ 1
5
#1 opened 4 months ago
by rombodawg
text benchmark ?
👍 3
1
#1 opened 4 months ago
by 
pypry
Can you do the newest deep seek models???
1
#1 opened 4 months ago
by rombodawg
Version based on Qwen-30-a3b or Granite 4.0 small?
#3 opened 6 months ago
by rombodawg
## License incompatibility: Apache-2.0 License is Incompatible with LLaMA 3 License
2
#5 opened 10 months ago
by 
xixi126
Can we have some more popular benchmarks
1
#8 opened 12 months ago
by rombodawg
BEST SYSTEM PROMPT. HUGE PERFORMANCE IMPROVEMENT
👍 5
4
#7 opened about 1 year ago
by rombodawg
Crazy good for its size
➕ 4
6
#11 opened about 1 year ago
by rombodawg
Please make i1 quants of my latest 72b model
18
#1 opened about 1 year ago
by rombodawg
LM Studio problems for Jinja template of QwQ-32B
4
#2 opened about 1 year ago
by 
ISK-VAGR
[bot] Conversion to Parquet
#1 opened about 1 year ago
by 
parquet-converter
Librarian Bot: Add language metadata for dataset
#2 opened about 1 year ago
by 
librarian-bot
Please make i1 quants of my latest 72b model
18
#1 opened about 1 year ago
by rombodawg