HF中国镜像站

ValueFX9507
/

Tifa-DeepsexV2-7b-MGRPO-GGUF-Q8

Reinforcement Learning

incremental-pretraining

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (1)

期待用QwQ:32b版本训练，7b的联想发散能力差点意思

#8 opened 3 days ago by

wired performance between 7b nocot cot and normal version

#6 opened 16 days ago by

安装时，如何指定“Files and versions”列出的某个特定版本

#5 opened 18 days ago by

为何总是在输出完文字后又画线盖掉

#4 opened 24 days ago by

官网的大号Tifa模型实际上是Claude API，您为何要谎称您有大模型？

#3 opened 24 days ago by deleted

ollama deploy problem

#2 opened 24 days ago by

Why is v2 only available as a 7B model? I'm hoping for 14B or 32B versions of the v2 model to be released. Thanks.

#1 opened 25 days ago by