| client_llm: | |
| url: "" # <-- start your own inference endpoint and provide url here (or use https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta) | |
| 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 https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-70B-Instruct) | |
| 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 | |