feat(*):增加了一些模型

anythinllm/.env

@@ -35,7 +35,7 @@ JWT_SECRET="Mnx6P2gPXDz1FngbX3Vmn9SB4T2EVeE4JDkrqM2biA0o6nrWxDNE34QTXzxSR7ToKpTn
 
 # LLM_PROVIDER='localai'
 LOCAL_AI_BASE_PATH='http://host.docker.internal:10580/v1'
-LOCAL_AI_MODEL_PREF='DeepSeek-R1-Distill-Llama-70B-AWQ'
+LOCAL_AI_MODEL_PREF='deepseek-r1:671b'
 LOCAL_AI_MODEL_TOKEN_LIMIT=8192
 LOCAL_AI_API_KEY="O8Is3NSYnp5fICWFbhkbwpLWgvMLkdCSuXR5ZggLmgwTKNPEWsjx1NqUxkyU7wLX"
 

chattts/compose.yaml

@@ -13,7 +13,7 @@ services:
               count: all
               capabilities:
                 - gpu
-    restart: always
+    restart: unless-stopped
     command: python webui.py
     runtime: nvidia
 x-dockge:

comfyui/compose.yaml

@@ -1,14 +1,14 @@
 version: "3.8"
 services:
   comfyui:
-    image: docker.citory.tech/mirror/yanwk/comfyui-boot:cu121
+    image: docker.citory.tech/mirror/yanwk/comfyui-boot:cu124-cn
     container_name: comfyui
     ports:
       - 10587:8188
     volumes:
-      - /home/deepgeek/data/data_local/server/comfyui/storage:/home/runner
+      - /home/deepgeek/data/data_base/comfyui/storage/ComfyUI:/root/ComfyUI
-      - /home/deepgeek/data/data_local/server/sd-models/checkpoints:/home/runner/ComfyUI/models/checkpoints
+      - /home/deepgeek/data/data_base/sd-models/checkpoints:/root/ComfyUI/models/checkpoints
-      - /home/deepgeek/data/data_local/server/sd-models/loras:/home/runner/ComfyUI/models/loras
+      - /home/deepgeek/data/data_base/sd-models/loras:/root/ComfyUI/models/loras
     deploy:
       resources:
         reservations:
@@ -19,7 +19,7 @@ services:
                 - compute
                 - utility
                 - gpu
-    restart: always
+    restart: unless-stopped
     runtime: nvidia
 x-dockge:
   urls:

dbgpt/.env

@@ -0,0 +1 @@
+# VARIABLE=value #comment

dbgpt/compose.yaml

@@ -0,0 +1,23 @@
+services:
+  dbgpt:
+    image: docker.citory.tech/mirror/eosphorosai/dbgpt-openai:latest
+    container_name: dbgpt
+    environment:
+      - SILICONFLOW_API_KEY=sk-tlsrjadpcrvebqdmptabfrxznnuiimsawowtpnzbokpanfcx
+    volumes:
+      - dbgpt-data:/app/pilot/data
+      - dbgpt-message:/app/pilot/message
+    ports:
+      - 10506:5670/tcp
+    # webserver may be failed, it must wait all sqls in /docker-entrypoint-initdb.d execute finish.
+    restart: unless-stopped
+    ipc: host
+    tty: true
+    stdin_open: true
+volumes:
+  dbgpt-data:
+  dbgpt-message:
+x-dockge:
+  urls:
+    - http://local.citory.tech:10506
+networks: {}

nlp/compose.yaml

@@ -13,5 +13,5 @@ services:
               count: all
               capabilities:
                 - gpu
-    restart: always
+    restart: unless-stopped
     runtime: nvidia

ollama/compose.yaml

@@ -18,7 +18,7 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_base/ollama:/root/.ollama
-    restart: always
+    restart: unless-stopped
     command: ollama run gemma3:27b
 x-dockge:
   urls:

open-webui/compose.yaml

@@ -1,13 +1,13 @@
 version: "3.8"
 services:
   open-webui:
-    image: docker.citory.tech/mirror/backplane/open-webui:0.5.20
+    image: docker.citory.tech/mirror/backplane/open-webui:0
     container_name: open-webui
     ports:
       - 10503:8080
     environment:
-      - OPENAI_API_KEY='' # 替换为您的 OpenAI API 密钥
+      - OPENAI_API_KEY=''
-      - OPENAI_API_BASE_URL=http://host.docker.internal:10580/v1 # 替换为您的 VLLM IP 和端口
+      - OPENAI_API_BASE_URL=http://host.docker.internal:10580/v1
       - WHISPER_MODEL=large
       - ENABLE_OLLAMA_API=true
       - OLLAMA_BASE_URL=http://host.docker.internal:10580
@@ -27,3 +27,4 @@ services:
 x-dockge:
   urls:
     - http://local.citory.tech:10503
+networks: {}

owlsam/compose.yaml

@@ -14,7 +14,7 @@ services:
               count: all
               capabilities:
                 - gpu
-    restart: always
+    restart: unless-stopped
     runtime: nvidia
 x-dockge:
   urls:

ragflow/.env

@@ -0,0 +1,148 @@
+# The type of doc engine to use.
+# Available options:
+# - `elasticsearch` (default) 
+# - `infinity` (https://github.com/infiniflow/infinity)
+DOC_ENGINE=${DOC_ENGINE:-elasticsearch}
+
+# ------------------------------
+# docker env var for specifying vector db type at startup
+# (based on the vector db type, the corresponding docker
+# compose profile will be used)
+# ------------------------------
+COMPOSE_PROFILES=${DOC_ENGINE}
+
+# The version of Elasticsearch.
+STACK_VERSION=8.11.3
+
+# The hostname where the Elasticsearch service is exposed
+ES_HOST=es01
+
+# The port used to expose the Elasticsearch service to the host machine, 
+# allowing EXTERNAL access to the service running inside the Docker container.
+ES_PORT=1200
+
+# The password for Elasticsearch. 
+ELASTIC_PASSWORD=infini_rag_flow
+
+# The port used to expose the Kibana service to the host machine, 
+# allowing EXTERNAL access to the service running inside the Docker container.
+KIBANA_PORT=6601
+KIBANA_USER=rag_flow
+KIBANA_PASSWORD=infini_rag_flow
+
+# The maximum amount of the memory, in bytes, that a specific Docker container can use while running.
+# Update it according to the available memory in the host machine.
+MEM_LIMIT=8073741824
+
+# The hostname where the Infinity service is exposed
+INFINITY_HOST=infinity
+
+# Port to expose Infinity API to the host
+INFINITY_THRIFT_PORT=23817
+INFINITY_HTTP_PORT=23820
+INFINITY_PSQL_PORT=5432
+
+# The password for MySQL. 
+MYSQL_PASSWORD=infini_rag_flow
+# The hostname where the MySQL service is exposed
+MYSQL_HOST=mysql
+# The database of the MySQL service to use
+MYSQL_DBNAME=rag_flow
+# The port used to expose the MySQL service to the host machine, 
+# allowing EXTERNAL access to the MySQL database running inside the Docker container. 
+MYSQL_PORT=5455
+
+# The hostname where the MinIO service is exposed
+MINIO_HOST=minio
+# The port used to expose the MinIO console interface to the host machine, 
+# allowing EXTERNAL access to the web-based console running inside the Docker container. 
+MINIO_CONSOLE_PORT=9001
+# The port used to expose the MinIO API service to the host machine, 
+# allowing EXTERNAL access to the MinIO object storage service running inside the Docker container. 
+MINIO_PORT=9000
+# The username for MinIO. 
+# When updated, you must revise the `minio.user` entry in service_conf.yaml accordingly.
+MINIO_USER=rag_flow
+# The password for MinIO. 
+# When updated, you must revise the `minio.password` entry in service_conf.yaml accordingly.
+MINIO_PASSWORD=infini_rag_flow
+
+# The hostname where the Redis service is exposed
+REDIS_HOST=redis
+# The port used to expose the Redis service to the host machine, 
+# allowing EXTERNAL access to the Redis service running inside the Docker container.
+REDIS_PORT=6380
+# The password for Redis.
+REDIS_PASSWORD=infini_rag_flow
+
+# The port used to expose RAGFlow's HTTP API service to the host machine, 
+# allowing EXTERNAL access to the service running inside the Docker container.
+SVR_HTTP_PORT=9380
+HTTP_PORT=10502
+# The RAGFlow Docker image to download.
+# Defaults to the v0.17.2-slim edition, which is the RAGFlow Docker image without embedding models.
+RAGFLOW_IMAGE=docker.citory.tech/mirror/infiniflow/ragflow:v0.17.2
+#
+# To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
+# RAGFLOW_IMAGE=infiniflow/ragflow:v0.17.2
+# 
+# The Docker image of the v0.17.2 edition includes:
+# - Built-in embedding models:
+#   - BAAI/bge-large-zh-v1.5
+#   - BAAI/bge-reranker-v2-m3
+#   - maidalun1020/bce-embedding-base_v1
+#   - maidalun1020/bce-reranker-base_v1
+# - Embedding models that will be downloaded once you select them in the RAGFlow UI:
+#   - BAAI/bge-base-en-v1.5
+#   - BAAI/bge-large-en-v1.5
+#   - BAAI/bge-small-en-v1.5
+#   - BAAI/bge-small-zh-v1.5
+#   - jinaai/jina-embeddings-v2-base-en
+#   - jinaai/jina-embeddings-v2-small-en
+#   - nomic-ai/nomic-embed-text-v1.5
+#   - sentence-transformers/all-MiniLM-L6-v2
+#
+# 
+
+
+# If you cannot download the RAGFlow Docker image:
+#
+# - For the `nightly-slim` edition, uncomment either of the following:
+# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly-slim
+# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly-slim
+#
+# - For the `nightly` edition, uncomment either of the following:
+# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly
+# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly
+
+# The local time zone.
+TIMEZONE='Asia/Shanghai'
+
+# Uncomment the following line if you have limited access to huggingface.co:
+HF_ENDPOINT=https://hf-mirror.com
+
+# Optimizations for MacOS
+# Uncomment the following line if your operating system is MacOS:
+# MACOS=1
+
+# The maximum file size for each uploaded file, in bytes.
+# You can uncomment this line and update the value if you wish to change the 1024M file size limit
+# MAX_CONTENT_LENGTH=1073741824
+# After making the change, ensure you update `client_max_body_size` in nginx/nginx.conf correspondingly.
+
+# The log level for the RAGFlow's owned packages and imported packages.
+# Available level:
+# - `DEBUG`
+# - `INFO` (default)
+# - `WARNING`
+# - `ERROR`
+# For example, following line changes the log level of `ragflow.es_conn` to `DEBUG`:
+# LOG_LEVELS=ragflow.es_conn=DEBUG
+
+# aliyun OSS configuration
+# STORAGE_IMPL=OSS
+# ACCESS_KEY=xxx
+# SECRET_KEY=eee
+# ENDPOINT=http://oss-cn-hangzhou.aliyuncs.com
+# REGION=cn-hangzhou
+# BUCKET=ragflow65536

ragflow/compose.yaml

@@ -0,0 +1,181 @@
+services:
+  es01:
+    container_name: ragflow-es-01
+    profiles:
+      - elasticsearch
+    image: docker.citory.tech/mirror/elasticsearch:${STACK_VERSION}
+    volumes:
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/data/esdata01:/usr/share/elasticsearch/data
+    ports:
+      - ${ES_PORT}:9200
+    env_file: .env
+    environment:
+      - node.name=es01
+      - ELASTIC_PASSWORD=${ELASTIC_PASSWORD}
+      - bootstrap.memory_lock=false
+      - discovery.type=single-node
+      - xpack.security.enabled=true
+      - xpack.security.http.ssl.enabled=false
+      - xpack.security.transport.ssl.enabled=false
+      - cluster.routing.allocation.disk.watermark.low=5gb
+      - cluster.routing.allocation.disk.watermark.high=3gb
+      - cluster.routing.allocation.disk.watermark.flood_stage=2gb
+      - TZ=${TIMEZONE}
+    mem_limit: ${MEM_LIMIT}
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1
+    healthcheck:
+      test: ["CMD-SHELL", "curl http://localhost:9200"]
+      interval: 10s
+      timeout: 10s
+      retries: 120
+    networks:
+      - ragflow
+    restart: on-failure
+
+  infinity:
+    container_name: ragflow-infinity
+    profiles:
+      - infinity
+    image: docker.citory.tech/mirror/infiniflow/infinity:v0.6.0-dev3
+    volumes:
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/data/infinity_data:/var/infinity
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/infinity_conf.toml:/infinity_conf.toml
+    command: ["-f", "/infinity_conf.toml"]
+    ports:
+      - ${INFINITY_THRIFT_PORT}:23817
+      - ${INFINITY_HTTP_PORT}:23820
+      - ${INFINITY_PSQL_PORT}:5432
+    env_file: .env
+    environment:
+      - TZ=${TIMEZONE}
+    mem_limit: ${MEM_LIMIT}
+    ulimits:
+      nofile:
+        soft: 500000
+        hard: 500000
+    networks:
+      - ragflow
+    healthcheck:
+      test: ["CMD", "curl", "http://localhost:23820/admin/node/current"]
+      interval: 10s
+      timeout: 10s
+      retries: 120
+    restart: on-failure
+
+
+  mysql:
+    # mysql:5.7 linux/arm64 image is unavailable.
+    image: docker.citory.tech/mirror/mysql:8.0.39
+    container_name: ragflow-mysql
+    env_file: .env
+    environment:
+      - MYSQL_ROOT_PASSWORD=${MYSQL_PASSWORD}
+      - TZ=${TIMEZONE}
+    command:
+      --max_connections=1000
+      --character-set-server=utf8mb4
+      --collation-server=utf8mb4_unicode_ci
+      --default-authentication-plugin=mysql_native_password
+      --tls_version="TLSv1.2,TLSv1.3"
+      --init-file /data/application/init.sql
+    ports:
+      - ${MYSQL_PORT}:3306
+    volumes:
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/data/mysql_data:/var/lib/mysql
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/init.sql:/data/application/init.sql
+    networks:
+      - ragflow
+    healthcheck:
+      test: ["CMD", "mysqladmin" ,"ping", "-uroot", "-p${MYSQL_PASSWORD}"]
+      interval: 10s
+      timeout: 10s
+      retries: 3
+    restart: on-failure
+
+  minio:
+    image: docker.citory.tech/mirror/minio/minio:RELEASE.2023-12-20T01-00-02Z
+    container_name: ragflow-minio
+    command: server --console-address ":9001" /data
+    ports:
+      - ${MINIO_PORT}:9000
+      - ${MINIO_CONSOLE_PORT}:9001
+    env_file: .env
+    environment:
+      - MINIO_ROOT_USER=${MINIO_USER}
+      - MINIO_ROOT_PASSWORD=${MINIO_PASSWORD}
+      - TZ=${TIMEZONE}
+    volumes:
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/data/minio_data:/data
+    networks:
+      - ragflow
+    restart: on-failure
+
+  redis:
+    # swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/valkey/valkey:8
+    image: docker.citory.tech/mirror/valkey/valkey:8
+    container_name: ragflow-redis
+    command: redis-server --requirepass ${REDIS_PASSWORD} --maxmemory 128mb --maxmemory-policy allkeys-lru
+    env_file: .env
+    ports:
+      - ${REDIS_PORT}:6379
+    volumes:
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/data/redis_data:/data
+    networks:
+      - ragflow
+    restart: on-failure
+    
+  ragflow:
+    depends_on:
+      mysql:
+        condition: service_healthy
+    image: ${RAGFLOW_IMAGE}
+    container_name: ragflow-server
+    ports:
+      - ${SVR_HTTP_PORT}:9380
+      - ${HTTP_PORT}:80
+      # - 443:443
+    volumes:
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/ragflow-logs:/ragflow/logs
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/nginx/proxy.conf:/etc/nginx/proxy.conf
+      - /home/deepgeek/data/data_local/server/ragflow/ragflow-docker/nginx/nginx.conf:/etc/nginx/nginx.conf
+    env_file: .env
+    environment:
+      - TZ=${TIMEZONE}
+      - HF_ENDPOINT=${HF_ENDPOINT}
+      - MACOS=${MACOS}
+    networks:
+      - ragflow
+    restart: on-failure
+    # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
+    # If you're using Docker Desktop, the --add-host flag is optional. This flag makes sure that the host's internal IP gets exposed to the Prometheus container.
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+  # executor:
+  #   depends_on:
+  #     mysql:
+  #       condition: service_healthy
+  #   image: ${RAGFLOW_IMAGE}
+  #   container_name: ragflow-executor
+  #   volumes:
+  #     - ./ragflow-logs:/ragflow/logs
+  #     - ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf
+  #   env_file: .env
+  #   environment:
+  #     - TZ=${TIMEZONE}
+  #     - HF_ENDPOINT=${HF_ENDPOINT}
+  #     - MACOS=${MACOS}
+  #   entrypoint: "/ragflow/entrypoint_task_executor.sh 1 3"
+  #   networks:
+  #     - ragflow
+  #   restart: on-failure
+  #   # https://docs.docker.com/engine/daemon/prometheus/#create-a-prometheus-configuration
+  #   # If you're using Docker Desktop, the --add-host flag is optional. This flag makes sure that the host's internal IP gets exposed to the Prometheus container.
+  #   extra_hosts:
+  #     - "host.docker.internal:host-gateway"
+networks:
+  ragflow:
+    driver: bridge

stable-diffusion-webui/compose.yaml

@@ -6,11 +6,11 @@ services:
     ports:
       - 10588:7860
     volumes:
-      - /home/deepgeek/data/data_local/server/stable-diffusion-webui-docker/data:/data
+      - /home/deepgeek/data/data_base/stable-diffusion-webui-docker/data:/data
-      - /home/deepgeek/data/data_local/server/stable-diffusion-webui-docker/data/config/auto/localizations:/stable-diffusion-webui/localizations
+      - /home/deepgeek/data/data_base/stable-diffusion-webui-docker/data/config/auto/localizations:/stable-diffusion-webui/localizations
-      - /home/deepgeek/data/data_local/server/stable-diffusion-webui-docker/output:/output
+      - /home/deepgeek/data/data_base/stable-diffusion-webui-docker/output:/output
-      - /home/deepgeek/data/data_local/server/sd-models/checkpoints:/data/models/Stable-diffusion
+      - /home/deepgeek/data/data_base/sd-models/checkpoints:/data/models/Stable-diffusion
-      - /home/deepgeek/data/data_local/server/sd-models/loras:/data/models/Lora
+      - /home/deepgeek/data/data_base/sd-models/loras:/data/models/Lora
     tty: true
     environment:
       - CUDA_LAUNCH_BLOCKING=1
@@ -26,7 +26,7 @@ services:
                 - compute
                 - utility
                 - gpu
-    restart: always
+    restart: unless-stopped
     runtime: nvidia
 x-dockge:
   urls:

toolbox-ocr/compose.yaml

@@ -13,7 +13,7 @@ services:
               count: all
               capabilities:
                 - gpu
-    restart: always
+    restart: unless-stopped
     runtime: nvidia
 x-dockge:
   urls:

vllm-deepseek-r1-32b/compose.yaml

@@ -17,13 +17,13 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_local/server/vllm/models:/models
-    restart: always
+    restart: unless-stopped
-    command: --served-model-name deepseek-r1:32b越狱 --model
+    command: --served-model-name deepseek-r1:32b --model
       /models/huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
       --trust-remote-code --host 0.0.0.0 --port 8080 --max-model-len 8192
       --tensor-parallel-size 2 --gpu_memory_utilization 0.9 --enforce-eager
-      --dtype auto --swap-space 8 --enable-auto-tool-choice
+      --dtype auto --swap-space 8 --enable-auto-tool-choice --tool-call-parser
-      --tool-call-parser pythonic
+      pythonic
 x-dockge:
   urls:
     - http://local.citory.tech:10580

vllm-deepseek-r1-70b/compose.yaml

@@ -18,12 +18,12 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_local/server/vllm/models:/models
-    restart: always
+    restart: unless-stopped
-    command: --served-model-name deepseek-r1:70b越狱 --model
+    command: --served-model-name deepseek-r1:70b 
-      /models/Fasiany/DeepSeek-R1-Distill-Llama-70B-abliterated-GPTQ-int4
+      --model /models/Valdemardi/DeepSeek-R1-Distill-Llama-70B-AWQ
-      --trust-remote-code --host 0.0.0.0 --port 8080 --enable-auto-tool-choice --tool-call-parser pythonic --max-model-len 8192
+      --trust-remote-code --host 0.0.0.0 --port 8080 --enable-auto-tool-choice
-      --tensor-parallel-size 2 --gpu_memory_utilization 0.9 --enforce-eager
+      --tool-call-parser pythonic --max-model-len 8192 --tensor-parallel-size 2
-      --dtype auto --swap-space 8 
+      --gpu_memory_utilization 0.9 --enforce-eager --dtype auto --swap-space 8
 x-dockge:
   urls:
     - http://local.citory.tech:10580

vllm-qwen25-72b-instruct-awq/compose.yaml

@@ -18,12 +18,12 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_local/server/vllm/models:/models
-    restart: always
+    restart: unless-stopped
-    command: --served-model-name Qwen2.5-72B-Instruct-AWQ --model /models/Qwen/Qwen2.5-72B-Instruct-AWQ
+    command: --served-model-name Qwen2.5:72b --model
-      --trust-remote-code --host 0.0.0.0 --port 8080 --max-model-len 8192
+      /models/Qwen/Qwen2.5-72B-Instruct-AWQ --trust-remote-code --host 0.0.0.0
-      --tensor-parallel-size 2 --gpu_memory_utilization 0.9 --enforce-eager
+      --port 8080 --max-model-len 8192 --tensor-parallel-size 2
-      --dtype auto --swap-space 8 --enable-auto-tool-choice --tool-call-parser
+      --gpu_memory_utilization 0.9 --enforce-eager --dtype auto --swap-space 8
-      llama3_json
+      --enable-auto-tool-choice --tool-call-parser llama3_json
 x-dockge:
   urls:
     - http://local.citory.tech:10580

vllm-qwen25-coder-32b-instruct/compose.yaml

@@ -18,8 +18,8 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_local/server/vllm/models:/models
-    restart: always
+    restart: unless-stopped
-    command: --served-model-name Qwen2.5-Coder-32B-Instruct --model
+    command: --served-model-name Qwen2.5-Coder:32b --model
       /models/Qwen/Qwen2.5-Coder-32B-Instruct --trust-remote-code --host 0.0.0.0
       --port 8080 --max-model-len 8192 --tensor-parallel-size 2
       --gpu_memory_utilization 0.9 --enforce-eager --dtype auto --swap-space 8

vllm-qwen25-vl-32b-instruct/compose.yaml

@@ -18,8 +18,8 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_local/server/vllm/models:/models
-    restart: always
+    restart: unless-stopped
-    command: --served-model-name Qwen2.5-VL-32B-Instruct --model
+    command: --served-model-name Qwen2.5-VL:32b --model
       /models/Qwen/Qwen2.5-VL-32B-Instruct --trust-remote-code --host 0.0.0.0
       --port 8080 --max-model-len 8192 --tensor-parallel-size 2
       --gpu_memory_utilization 0.9 --enforce-eager --dtype auto --swap-space 8

vllm-qwq-32b/compose.yaml

@@ -18,12 +18,12 @@ services:
     runtime: nvidia
     volumes:
       - /home/deepgeek/data/data_local/server/vllm/models:/models
-    restart: always
+    restart: unless-stopped
-    command: --served-model-name QwQ-32B --model /models/Qwen/QwQ-32B
+    command: --served-model-name QwQ:32b --model /models/Qwen/QwQ-32B
       --trust-remote-code --host 0.0.0.0 --port 8080 --max-model-len 8192
       --tensor-parallel-size 2 --gpu_memory_utilization 0.9 --enforce-eager
-      --dtype auto --swap-space 8 --enable-auto-tool-choice
+      --dtype auto --swap-space 8 --enable-auto-tool-choice --tool-call-parser
-      --tool-call-parser llama3_json
+      llama3_json
 x-dockge:
   urls:
     - http://local.citory.tech:10580