hunyuan-1.8b 转换onnx 模型时 BitShift算子出现这个 tensor(int32)无效 是layers.31网络层出现什么问题吗?
#8 opened 1 day ago
by
YouLei0106

请问是否能提供Hunyuan-7B的math分数相关的细节?
#7 opened 2 days ago
by
beyoung
Why this model uses a different tokenizer from other variants (0.5B/1.8B/4B)?
#6 opened 4 days ago
by
J22
not able to use this model (tencent/Hunyuan-7B-Instruct) via vllm
➕
7
2
#5 opened 5 days ago
by
aditya-shinde

Readme says 256k context, but config.json has "max_position_embeddings": 32768
#4 opened 5 days ago
by
stev236
Local Installation Video and Testing - Step by Step
😎
1
1
#2 opened 5 days ago
by
fahdmirzac

Update README.md
#1 opened 5 days ago
by
woodchen7
