{
  "apply_clip": true,
  "autoawq_version": "0.2.9",
  "bits": 4,
  "calibration_max_chars": null,
  "calibration_max_tokens": 2048,
  "calibration_min_chars": 256,
  "calibration_samples": 128,
  "calibration_seed": 7,
  "command": [
    "terminal_agent_demo/scripts/quantize_openthinker_awq.py",
    "--output-dir",
    "quantization/models/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
    "--repo-id",
    "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
    "--samples",
    "128",
    "--max-tokens",
    "2048",
    "--max-calib-seq-len",
    "2048",
    "--n-parallel-calib-samples",
    "1",
    "--max-chunk-memory-mb",
    "256",
    "--group-size",
    "128",
    "--device-map",
    "auto",
    "--max-shard-size",
    "5GB"
  ],
  "cuda_version": "12.8",
  "device_map": "auto",
  "duo_scaling": true,
  "elapsed_seconds": 12111.596,
  "finished_at_utc": "2026-06-25T01:31:16.596143+00:00",
  "group_size": 128,
  "max_calib_seq_len": 2048,
  "max_chunk_memory_mb": 256,
  "modules_to_not_convert": [
    "lm_head"
  ],
  "n_parallel_calib_samples": 1,
  "output_dir": "/wbl-fast/usrs/ee/clean-20260619/worktrees/terminal-agent-rl-opd-qwen3-4b/quantization/models/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
  "repo_id": "eewer/OpenThinkerAgent-32B-AWQ-Int4-Terminus2",
  "source_dataset": "/wbl-fast/usrs/ee/clean-20260619/terminal-agent-rl/areal_runs/terminal-agent-demo/data/skill_based_medium.even.terminus2.slime_messages.jsonl",
  "source_model": "open-thoughts/OpenThinkerAgent-32B",
  "source_revision": "65d8a62b87c8d3d34bc45108a7ad87635318db9f",
  "started_at_utc": "2026-06-24T22:09:24.999975+00:00",
  "torch_version": "2.11.0+cu128",
  "transformers_version": "5.12.1",
  "version": "GEMM",
  "zero_point": true
}