update functioncall
#16 opened 8 days ago
by
kamuy-shennai

HF Compatible Weights
1
#15 opened 8 days ago
by
geetu040

How to get structrured output?
#14 opened 9 days ago
by
Sheffchenko

使用vllm推理部署,对比了DeepSeek- R1和MiniMax-M1-80k的性能,差距很大,是什么原因?
1
#13 opened 10 days ago
by
dingyuansheng
Quantization Support
#12 opened 11 days ago
by
Wongibaek
Was the 7.5T Token Continual Pre-Training Performed on the Instruction-Tuned Model or the Base PLM?
3
#10 opened 15 days ago
by
Jinhwan
I hope you guys can provide a 32B dense model
👍
3
#9 opened 17 days ago
by
zletpm
MLX Convert Error
4
#8 opened 17 days ago
by
baggaindia
main
#7 opened 19 days ago
by
zwb19820615
Where's the knowledge?
🧠
❤️
7
6
#5 opened 21 days ago
by
phil111
Can we expect a 20b~32b parameter minimax model to fit into a single 4090?
🚀
🔥
36
#3 opened 22 days ago
by
win10

WHAT a benchmarks graph
👍
13
1
#2 opened 22 days ago
by
CyborgPaloma
gguf weights for llama.cpp?
👍
🧠
23
1
#1 opened 22 days ago
by
segmond