model_name:
  # - "mistral-7B-instruct-v0.2"
  - "llama2-7b-chat-4k"
  # - "chatglm4-9b"
  # - "qwen2-7b-instruct"

full_kv: True
optimize_model: True
dtype: 'fp16'
low_bit: 'sym_int4'

e: False

compress_kv:
  - "ablation_c512_w32_k7_maxpool"
  - "ablation_c1024_w32_k7_maxpool"

datasets:
  - "multi_news"
  - "qasper"
  - "hotpotqa"
  - "trec"
  - "passage_count"
  - "lcc"
  # - "multifieldqa_zh"
  # - "dureader"
  # - "vcsum"
  # - "lsht"
  # - "passage_retrieval_zh"