cpatonn's picture
Update README.md
2e7b0b5 verified
metadata
license: apache-2.0
base_model:
  - nvidia/OpenReasoning-Nemotron-7B
datasets:
  - mit-han-lab/pile-val-backup

OpenReasoning-Nemotron-7B-AWQ

Method

Quantised using vllm-project/llm-compressor and the following configs:

recipe = [
    AWQModifier(ignore=["lm_head"], scheme="W4A16_ASYM", targets=["Linear"]),
]