gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
70
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
During the “Quantize your own model” workflow, the runtime loads calibration datasets via `datasets.load_dataset(...)` (e.g., C4/ShareGPT/unfiltered datasets) and uses their text (e.g., `example["text"]` / `example["content"]` / `example["conversations"]`) to build `calibration_data`, which becomes LLM-readable token text fed into the model/LLM pipeline—an outsider-authored free-text source.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The integration guide includes a docker run that pulls and runs the remote container image ghcr.io/huggingface/text-generation-inference:latest at runtime, which fetches and executes remote code (ghcr.io/huggingface/text-generation-inference:latest).
- Repository
- synthetic-sciences/openscience
- Commit
52845c3
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.