Model reference · open weights
ShieldLM-chatglm3 is an open-weight embedding model from thu-coai. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | thu-coai |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 6.2B |
| Runs with | transformers |
| Released | 2024-02-26 |
| Popularity | 2k downloads / month |
| Licence | Open weights |
About
The ShieldLM model (paper link) initialized from chatglm3-6b. ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with general human safety standards, supports fine-grained customizable detection rules, and provides explanations for its decisions. Refer to our github repository for more detailed information.
Please refer to our github repository for the detailed usage instructions.
ShieldLM demonstrates impressive detection performance across 4 ID and OOD test sets, compared to strong baselines such as GPT-4, Llama Guard and Perspective API. Refer to our paper for more detailed evaluation results.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys shieldlm-chatglm3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (shieldlm-chatglm3 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"shieldlm-chatglm3","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.