{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "datamllab-openebfm--evaluate-checkpoint-bpb-and-qa",
 "repo": "datamllab/OpenEBFM",
 "repo_url": "https://github.com/datamllab/OpenEBFM",
 "repo_slug": "datamllab-openebfm",
 "title": "Measure BPB and QA scores for an EBFM checkpoint",
 "page_title": "How to measure BPB and QA scores for an EBFM checkpoint with Open EBFM",
 "summary": "Run position-wise BPB and QA evaluation on a published model and collect results.",
 "who": "A researcher comparing EBFM checkpoints who needs consistent benchmark numbers.",
 "problem": "Comparing language models needs the same metrics computed the same way across checkpoints.",
 "outcome": "Position-wise BPB and QA result files written under results/ for the chosen checkpoint.",
 "steps": [
  "Run `uv sync --extra gpu --extra hf --extra web` and `source .venv/bin/activate` to set up the environment.",
  "Download the local snapshot with `MODEL_DIR=\"$(python -c 'from huggingface_hub import snapshot_download; print(snapshot_download(repo_id=\"guan-wang/EBFM-DCLM-1B\"))')\"` so the BPB metric has token_bytes.pt.",
  "Run `bash runs/eval.sh --checkpoint guan-wang/EBFM-DCLM-1B --dataset dclm --data-dir data/dclm --tokenizer-path \"${MODEL_DIR}\" --output_root . --run_name eval-dclm` for BPB. (inferred, check the README)",
  "Run `bash runs/qa.sh --checkpoint guan-wang/EBFM-DCLM-1B --tokenizer-path \"${MODEL_DIR}\" --eval-bundle data/eval_bundle --output_root . --run_name qa-dclm` for QA. (inferred, check the README)"
 ],
 "agent_prompt": "In the datamllab/OpenEBFM repo, run runs/eval.sh for BPB and runs/qa.sh for QA on the checkpoint <hf_model_id>, using the local snapshot directory for the tokenizer path. Report the results/ paths and confirm token_bytes.pt was found in the snapshot.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "2 hours",
 "basis": "readme",
 "caveat": "BPB evaluation needs the local snapshot directory, and the eval bundle at data/eval_bundle must be prepared separately because the README says data is not included.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python with uv installed",
  "A GPU environment (the README installs the gpu extra and loads checkpoints with device=\"cuda\")",
  "Network access for data preparation and Hugging Face downloads",
  "Enough disk space for the datasets and checkpoints (sizes are not stated in the README)"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/datamllab-openebfm/evaluate-checkpoint-bpb-and-qa/",
 "md": "https://dedupedai.com/use-cases/datamllab-openebfm/evaluate-checkpoint-bpb-and-qa/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/datamllab-openebfm--evaluate-checkpoint-bpb-and-qa.json",
 "api_version": "v1"
}