Open-Bee/Bee-8B-SFT warn
Loading it runs custom code from the repo; the chat template was dropped from its base model, which changes behavior; its architecture doesn't match its claimed base model.
claims base: Qwen/Qwen3-8B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights batteryfailedBehavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | failedtensor model.language_model.embed_tokens.weight missing from model-00004-of-00004.safetensors header |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-21 · published from a community scan.
medium Repo ships executable Python (trust_remote_code)
The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.
How to fix
Review and pin the custom code; never float on `main` with trust_remote_code=True.
- Read every `.py` file in the repo before first load — this code runs in your process.
- Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
- Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.
medium Chat template dropped vs parent
Qwen/Qwen3-8B ships a chat template; this repo does not. Serving stacks will silently fall back to a generic template, changing behavior. (In our 296-model census, 78% of pure quantization re-releases changed or dropped the template.)
How to fixingot patch
Restore the parent's chat template in `tokenizer_config.json` — a pure metadata fix.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- Or fix by hand: copy the `chat_template` value from the parent repo's `tokenizer_config.json` into this model's, and pin your serving stack to that file.
- If the drift was intentional (the author retrained on a new template), confirm that in the model card before "fixing" it — restoring the parent template on retrained weights changes behavior too.
medium Architecture differs from claimed parent (Bee vs qwen3)
This model declares Qwen/Qwen3-8B as its base, but its config declares architecture 'Bee' while the parent is 'qwen3'. A finetune, merge, or quantization cannot change the architecture family — the lineage label is wrong or misleading, so treat provenance claims (training data, safety posture, licensing) as unverified.
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
Fix it
Some findings are metadata-level and patchable — apply the fixes to your local copy (your weights never leave your machine):
npx @ingotai/scan patch Open-Bee/Bee-8B-SFT
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Fingerprint
The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-21.
| architecture | Bee |
| parameters | 8675.0M |
| license | apache-2.0 |
| serialization | safetensors custom code |
| chat template | none |
| claimed lineage | Qwen/Qwen3-8B |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | BeeForConditionalGeneration |
| library | transformers |
| pipeline | image-text-to-text |
| repo files | 25 |
| revision | a81758f431a0 |
| HF snapshot | 1.6k downloads · 14 likes · updated 2026-03-10 · captured 2026-08-21 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/Open-Bee/Bee-8B-SFT)