metadata

license: apache-2.0
datasets:
  - lars1234/story_writing_benchmark
base_model:
  - lars1234/Mistral-Small-24B-Instruct-2501-writer

Mistral-Small-24B-Instruct-2501-writer-AWQ

This model is the 4-bit AWQ-quantized version of Mistral-Small-24B-Instruct-2501-writer.

Quantization Method: AWQ (Activation-aware Weight Quantization)
Quantization Configuration:
- Bit Width: 4-bit
- Group Size: 128
- Zero Point: Enabled
- Version: GEMM