Resources

View closed (19)

Inference speed issue with local deployment on H800

#44 opened 3 days ago by

jiutu

Token Count Calculation in SFT Data Distribution Curation

#42 opened 10 days ago by

tcy006

Actual guide for fine-tuning?

#41 opened 12 days ago by

openSourcerer9000

Model fails to load using transformers with trust_remote_code=True

#40 opened 13 days ago by

Pratikk25

Ambiguity on interleaved thinking

#38 opened 18 days ago by

jondurbin

Invalid reasoning-parser

#37 opened 18 days ago by

willamazon1

Low generation speed.

#36 opened 19 days ago by

Yurkoff

Question about XET storage: Why are some safetensors files 40 Bytes?

➕ 2

#35 opened 19 days ago by

yingchaox

mtp or other speculative decoding method?

#34 opened 21 days ago by

CHNtentes

Expanding context window via YARN

#33 opened 21 days ago by

sixxio

MiniMax-M2全方位最新实测出炉（300+维度），欢迎进群交流讨论~

#31 opened 22 days ago by

JEIN

Can it run on NVIDIA A100 80G * 8 ？

#30 opened 23 days ago by

jetto98

Interleaved Thinking, minimax:tool_call parsing

#29 opened 24 days ago by

0xSero

mixed results

#28 opened 24 days ago by

kingriel

Missing official chat_template / unclear initialization of <think> interleaving in MiniMax-M2 ?

#27 opened 25 days ago by

Serveurperso

Request: DOI

#26 opened 26 days ago by

sreeshanthpeddi

Request for 2000 Samples from training data for NVFP4 QUANTIZATION

❤️ 3

#25 opened 26 days ago by

jasonface

what data and its volume were used to train the model?

👍 1

#21 opened 29 days ago by

Pep0pi

230B vs 235B: Why no comparison against Qwen3-235B-A22B-Thinking-2507 ?

🤝 👍 2

#20 opened 29 days ago by

rtzurtz

AWQ Please

#18 opened 29 days ago by

darkstar3537

GGUF support

👀 ➕ 7

#17 opened 29 days ago by

geboh67859

Why does it keep trying to connect to huggingface?

#16 opened 30 days ago by

surak

About the LCB evaluation

➕ 2

#13 opened 30 days ago by

sayhitoday

YES!!

🚀 14

#12 opened 30 days ago by

CyborgPaloma

Speculative decoding

👍 3

#9 opened about 1 month ago by

adsfdgfhgjhk11