| client_llm: | |
| url: "" # <-- start your own inference endpoint and provide url here (or use /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2FHuggingFaceH4%2Fzephyr-7b-beta)%3C%2Fspan%3E%3C!-- HTML_TAG_END --> | |
| model_id: "HuggingFaceH4/zephyr-7b-beta" # <-- your client llm | |
| backend: HFChat | |
| max_tokens: 800 | |
| temperature: 0.6 | |
| expert_llm: | |
| url: "" # <-- start your own inference endpoint and provide url here (or use /static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2Fmeta-llama%2FMeta-Llama-3-70B-Instruct)%3C%2Fspan%3E%3C!-- HTML_TAG_END --> | |
| model_id: "meta-llama/Meta-Llama-3-70B-Instruct" | |
| backend: HFChat # <-- Currently supported: HFChat / VLLM / Fireworks | |
| classifier_llm: | |
| model_id: "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli" | |
| url: "" # <-- start your own inference endpoint of classifier model and provide url here | |
| batch_size: 8 | |