diff --git a/settings/settings-vllm-pgvector.yaml b/settings/settings-vllm-pgvector.yaml index 8a7ce245..598b46af 100644 --- a/settings/settings-vllm-pgvector.yaml +++ b/settings/settings-vllm-pgvector.yaml @@ -4,7 +4,6 @@ server: llm: mode: openailike - tokenizer: ${VLLM_TOKENIZER:lmsys/vicuna-7b-v1.5} max_new_tokens: ${VLLM_MAX_NEW_TOKENS:5000} context_window: ${VLLM_CONTEXT_WINDOW:4096} temperature: ${VLLM_TEMPERATURE:0.1} diff --git a/settings/settings.yaml b/settings/settings.yaml index 55511247..42642872 100644 --- a/settings/settings.yaml +++ b/settings/settings.yaml @@ -39,7 +39,6 @@ llm: # Should be matching the selected model max_new_tokens: 512 context_window: 3900 - tokenizer: mistralai/Mistral-7B-Instruct-v0.2 temperature: 0.1 # The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual. (Default: 0.1) rag: