DeepSeek V3 FP16 Atten NaN
This is a minimal reproduceable sample to let the final layer of DeepSeek V3's attention output NaNs when using data type float16.
Run the run.py to see the NaNs.
Weights are converted to bfloat16 using the original float8 e4m3fn, then converted to float16, then extracted from the final layer's attention.
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for v2ray/DeepSeek-V3-FP16-Atten-NaN
Base model
deepseek-ai/DeepSeek-V3