asdf
laterbreh
AI & ML interests
None yet
Organizations
None yet
Question about benchmark score (deepswe v1.1)
5
#50 opened 2 months ago
by
Ayuan0105
Running on 4x RTX PRO 6000 with NVMe offload for ngram
🚀 7
8
#28 opened 2 months ago
by
0xSero
smaller model with engram?
🔥 4
12
#32 opened 2 months ago
by
ProCreations
BenchMAXXXED
➕ 2
33
#28 opened 4 months ago
by
TawusGames
New Weights working on vllm DGX Spark -1 node setup - GOOD QUALITY
17
#25 opened 3 months ago
by
TeAmErX
Is there a recommended vLLM recipe for RTX Pro 6000?
3
#18 opened 4 months ago
by
DikiyLifter92
Instructions following mode
3
#32 opened 4 months ago
by
btvd
S 2.1 in agentic pipelines: restoring reasoning across turns, and a dead end on the looping mechanism
➕🔥 3
3
#31 opened 4 months ago
by deleted
Thank you
🔥 1
#2 opened 4 months ago
by
laterbreh
Model is decent, its faster than Qwen and pretty close on real world tool calls
❤️👀 3
7
#22 opened 4 months ago
by
Jakaryun
Model "thinks" away its context window or "thinks" into timeout.
➕ 4
3
#9 opened 4 months ago
by
laterbreh