hipnologo/falcon-7b-instruct-qlora-truthful-qa warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo; EOS ids disjoint between config.json and generation_config.json. Plus 1 more issue.
claims base: vilsonrodrigues/falcon-7b-instruct-sharded · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights batteryqueuedBehavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | queued |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-25 · published from a community scan.
medium Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (adapter_model.bin, pytorch_model-00001-of-00002.bin, pytorch_model-00002-of-00002.bin). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.
How to fix
Convert the weights to safetensors before loading them anywhere that matters.
- Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
- Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
- Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.
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 EOS ids disjoint between config.json and generation_config.json
config.json declares eos_token_id [11] while generation_config.json declares [2] with no overlap. Runtimes read one or the other, so at least one of them stops generation on the wrong token (or never). Align both files on the token the chat template actually ends turns with.
How to fixingot patch
Align the stop-token declarations — a pure metadata fix to `generation_config.json` (and `config.json`).
- Identify the token the chat template actually ends assistant turns with (e.g. `<|eot_id|>`, `<end_of_turn>`, `<|im_end|>`) and make sure its id is in `generation_config.json`'s `eos_token_id` list.
- Keep `config.json`'s `eos_token_id` consistent with (or a subset of) `generation_config.json`'s — runtimes differ in which file they read.
- For the pad-equals-EOS hazard: repoint `pad_token` at a dedicated padding token before fine-tuning; serving is unaffected.
- Until the repo is fixed, pass explicit stop tokens to your serving stack (e.g. vLLM `stop_token_ids`, llama.cpp `--override-kv tokenizer.ggml.eos_token_id`).
medium Architecture differs from claimed parent (RefinedWebModel vs falcon)
This model declares vilsonrodrigues/falcon-7b-instruct-sharded as its base, but its config declares architecture 'RefinedWebModel' while the parent is 'falcon'. 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 hipnologo/falcon-7b-instruct-qlora-truthful-qa
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 2026-08-25.
| architecture | RefinedWebModel · 32 layers · 4544-dim |
| vocabulary | 65,024 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle custom code |
| chat template | none |
| claimed lineage | vilsonrodrigues/falcon-7b-instruct-sharded |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | RWForCausalLM |
| library | peft |
| pipeline | text-generation |
| repo files | 12 — pickle: adapter_model.bin, pytorch_model-00001-of-00002.bin, pytorch_model-00002-of-00002.bin |
| revision | 6bf5e96a6186 |
| HF snapshot | 12 downloads · 2 likes · updated 2023-09-22 · captured 2026-08-25 |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | queued | 2026-08-25 22:41 | — | 0 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/hipnologo/falcon-7b-instruct-qlora-truthful-qa)