Create README.md
2b2872a
verified
Mixtral-8x7B-Instruct-v0.1-FP8-v1
- Weights and activations are per-tensor quantized to float8_e4m3.
- Quantization with AutoFP8.
- Calibration dataset: Ultrachat (mgoin/ultrachat_2k)
- Samples: 1024
- Sequence length: 8192
Evaluation
TBA