llm, add hugging face token to ollama.

2026-10-10 09:56:41 -07:00
parent 4ab93d02f4
commit c85d96f940
1 changed files with 9 additions and 1 deletions
@@ -197,25 +197,33 @@
            dest: "{{ ollama_runit_script }}"
            content: |
              #!/bin/sh -e
-              # Allow pulling and accessing LLMs via tools.
              exec 2>&1
+              # Allow pulling and accessing LLMs via tools.
+
              ### Required ###
              export HOME={{ user_user.home }}
+
              ### Timeouts ###
              export OLLAMA_LOAD_TIMEOUT=20m # default is 5m
              export OLLAMA_REQUEST_TIMEOUT=3600 # default 300 (unconfirmed, not in the list of --help vars)
+
              ### Resource Usage ###
              export OLLAMA_KEEP_ALIVE=20m # default is 5m
              export OLLAMA_MAX_LOADED_MODELS={{ llm_concurrency }} # default is 3 if using CPUs, or 3 * NumGPUs
              export OLLAMA_NUM_PARALLEL={{ llm_parallel }} # default is 1 and applies per-model (unconfirmed)
              export OLLAMA_CONTEXT_LENGTH={{ llm_context }} # default is 4096, https://docs.ollama.com/faq#how-can-i-specify-the-context-window-size
              export OLLAMA_MAX_QUEUE=999 # default is 512 (unconfirmed)
+
              ### Prevent Data Loss ###
              # OLLAMA_NOPRUNE
              #   Default is 0, which causes unfinished pulls to be deleted
              #   after 1 hour of inactivity. To manually clean partials, run:
              #     `rm ~/.ollama/models/blobs/*-partial*`
              export OLLAMA_NOPRUNE=1
+
+              ### Tokens ###
+              {{ ("export HF_TOKEN=" ~ hf_token) if hf_token else '' }}
+
              exec chpst -u {{ user }} ollama serve
            mode: "0755"