EPFLiGHT/Meditron3-8B warn
Loading it runs custom code from the repo; the chat template was dropped from its base model, which changes behavior.
claims base: meta-llama/Llama-3.1-8B-Instruct · 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 | failed403 Forbidden for https://huggingface.co/EPFLiGHT/Meditron3-8B/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope) |
| 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.
info Gated repository
Access requires accepting the owner's terms; check the gate conditions for redistribution and field-of-use limits.
How to fix
Read the gate terms before building on the model.
- Check the gate conditions on the Hugging Face repo for redistribution and field-of-use limits — they bind your deployment, not just your download.
info Gated repo files unreadable — file-level checks skipped
config.json and tokenizer_config.json could not be read, so chat-template, architecture, and vocab checks did not run. Full scans of gated repos need the service's HF_TOKEN account to have accepted this repo's license on Hugging Face.
How to fix
Read the gate terms before building on the model.
- Check the gate conditions on the Hugging Face repo for redistribution and field-of-use limits — they bind your deployment, not just your download.
medium Chat template dropped vs parent
meta-llama/Llama-3.1-8B-Instruct 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.
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 EPFLiGHT/Meditron3-8B
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 | llama |
| parameters | 8030.3M |
| license | llama3.1 |
| serialization | safetensors pickle custom code |
| chat template | none |
| claimed lineage | meta-llama/Llama-3.1-8B-Instruct |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 17 — pickle: scheduler.pt, training_args.bin |
| gated | auto |
| revision | 783c241b18b8 |
| HF snapshot | 686 downloads · 29 likes · updated 2026-06-25 · captured 2026-08-21 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/EPFLiGHT/Meditron3-8B)