61 lines
2.0 KiB
YAML
61 lines
2.0 KiB
YAML
# lfm-vl-uncensored-seat — ABLITERATED LFM2.5-VL-3B on nh3-ml1, running PARALLEL to
|
|
# the stock seat (stacks/lfm-vl-seat) so brokkr can A/B them. Stock tested censored
|
|
# on NSFW captioning; the operator wants an uncensored one (relayed by
|
|
# brokkr-smithy-dev, 2026-09-26). Same llama.cpp image and flags as the stock seat.
|
|
#
|
|
# llama-server SC117/LFM2.5-VL-3B-Uncensored-GGUF Q4_K_M + its mmproj Q8_0 :8032
|
|
#
|
|
# "Uncensored" is the repo's claim (abliterix Trial 65 merged into the official
|
|
# base). brokkr re-runs its 6-image eval against this seat to check it engages
|
|
# AND stays coherent. Direct only, no gateway entry, until that eval passes.
|
|
#
|
|
# Files (not in git): /opt/aimodels/gguf/lfm25-vl-3b-uncensored/ from
|
|
# SC117/LFM2.5-VL-3B-Uncensored-GGUF @ 7c1d3fb71e56.
|
|
name: lfm-vl-uncensored-seat
|
|
services:
|
|
llama-server:
|
|
image: ${LLAMACPP_IMAGE}
|
|
container_name: lfm-vl-uncensored
|
|
restart: unless-stopped
|
|
ports:
|
|
- "${VL_PORT}:8080"
|
|
volumes:
|
|
- /opt/aimodels/gguf/lfm25-vl-3b-uncensored:/models:ro
|
|
command:
|
|
- -m
|
|
- /models/${VL_MODEL_FILE}
|
|
- --mmproj
|
|
- /models/${VL_MMPROJ_FILE}
|
|
- --alias
|
|
- ${VL_ALIAS}
|
|
- --host
|
|
- 0.0.0.0
|
|
- --port
|
|
- "8080"
|
|
- -ngl
|
|
- "999"
|
|
- -c
|
|
- "${VL_CTX}"
|
|
- -np
|
|
- "${VL_PARALLEL}"
|
|
- --jinja
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids: ["0"]
|
|
capabilities: [gpu]
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-fsS", "http://localhost:8080/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
labels:
|
|
- homepage.group=AI - Eval & Retrieval
|
|
- homepage.name=VL — LFM2.5-VL-3B Uncensored (llama.cpp, nh3-ml1)
|
|
- homepage.icon=mdi-image-search
|
|
- homepage.description=Abliterated LFM2.5-VL-3B for the dataset foundry A/B (direct only)
|
|
- homepage.href=http://10.100.50.80:${VL_PORT}
|