Files
homelab/ansible/roles/llm-inference-multimodel/tasks/models.yml

100 lines
3.8 KiB
YAML

---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/tasks/models.yml
# DESCRIPTION: Phase 1 — download both GGUFs to {{ llm_models_dir }}.
# Idempotent: reuses the stat + size-threshold guard pattern
# from the llm-inference-homelab skill / roles/llm-inference's
# serve.yml, so reruns don't re-pull 8.5GB / 11.7GB files.
#
# Does NOT touch the existing Gemma GGUF — separate directory
# entries, no overlap, no deletion of anything pre-existing.
# ------------------------------------------------------------------------------
- name: Create models directory
ansible.builtin.file:
path: "{{ llm_models_dir }}"
state: directory
owner: "{{ llm_service_user }}"
group: "{{ llm_service_user }}"
mode: "0755"
become: true
# --- Aux model (Phi-4-14B Q4_K_M) --------------------------------------------
- name: Check if aux model GGUF already exists
ansible.builtin.stat:
path: "{{ llm_aux_model_path }}"
register: llm_aux_model_stat
- name: Download aux model — Phi-4-14B-Q4_K_M GGUF
ansible.builtin.get_url:
url: "{{ llm_aux_model_url }}"
dest: "{{ llm_aux_model_path }}"
headers:
Authorization: "Bearer {{ llm_hf_token }}"
owner: "{{ llm_service_user }}"
group: "{{ llm_service_user }}"
mode: "0644"
timeout: 7200
force: false
become: true
no_log: true
# Idempotency guard: skip if file exists and is above the min-size threshold
# (catches partial/truncated downloads from an interrupted prior run).
when: not llm_aux_model_stat.stat.exists or (llm_aux_model_stat.stat.size | int) < (llm_aux_model_min_bytes | int)
# --- Tool-calling model (Mistral-Small-24B Q3_K_M) ---------------------------
- name: Check if tool-calling model GGUF already exists
ansible.builtin.stat:
path: "{{ llm_toolcall_model_path }}"
register: llm_toolcall_model_stat
- name: Download tool-calling model — Mistral-Small-24B-Instruct-2501 Q3_K_M GGUF
ansible.builtin.get_url:
url: "{{ llm_toolcall_model_url }}"
dest: "{{ llm_toolcall_model_path }}"
headers:
Authorization: "Bearer {{ llm_hf_token }}"
owner: "{{ llm_service_user }}"
group: "{{ llm_service_user }}"
mode: "0644"
timeout: 7200
force: false
become: true
no_log: true
when: not llm_toolcall_model_stat.stat.exists or (llm_toolcall_model_stat.stat.size | int) < (llm_toolcall_model_min_bytes | int)
- name: Report model files present on disk
ansible.builtin.debug:
msg:
- "Aux model: {{ llm_aux_model_path }}"
- "Tool-calling model: {{ llm_toolcall_model_path }}"
# --- Tool-calling chat template override -------------------------------------
# Mistral-Small-24B-Instruct-2501's own embedded/tokenizer_config chat template
# has NO tool-call handling ([AVAILABLE_TOOLS]/[TOOL_CALLS] blocks) — confirmed
# via /props chat_template_caps.supports_tools=false against the stock
# template. Mistral-Nemo-Instruct-2407 ships a template with full tool-calling
# support and the same Mistral instruct format family, so we serve it via
# --chat-template-file instead of relying on GGUF-embedded metadata.
# See docs/validation-log.md for the investigation and probe results.
- name: Create chat templates directory
ansible.builtin.file:
path: "{{ llm_toolcall_chat_template_file | dirname }}"
state: directory
owner: "{{ llm_service_user }}"
group: "{{ llm_service_user }}"
mode: "0755"
become: true
- name: Deploy tool-calling-capable chat template (from Mistral-Nemo-Instruct-2407)
ansible.builtin.copy:
src: mistral-small-tool-use.jinja
dest: "{{ llm_toolcall_chat_template_file }}"
owner: "{{ llm_service_user }}"
group: "{{ llm_service_user }}"
mode: "0644"
become: true