log_path: "logs" log_level: "DEBUG" api_server: host: "127.0.0.1" port: 8000 publish_server: host: "127.0.0.1" port: 8001 openai_plugins_folder: - "/media/gpt4-pdf-chatbot-langchain/langchain-chatchat-archive/openai_plugins" openai_plugins_load_folder: - "/media/gpt4-pdf-chatbot-langchain/langchain-chatchat-archive/configs" plugins: - openai: name: "openai" - fastchat: name: "fastchat" logdir: "/media/gpt4-pdf-chatbot-langchain/langchain-chatchat-archive/logs" # LLM 运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。 llm_device: "auto" model_names: - "Qwen-1_8B-Chat" run_controller: host: "127.0.0.1" port: 20001 dispatch_method: "shortest_queue" run_openai_api: host: "127.0.0.1" port: 20000 fschat_model_workers: - default: host: "127.0.0.1" port: 20002 device: "auto" # False,'vllm',使用的推理加速框架,使用vllm如果出现HuggingFace通信问题，参见doc/FAQ # vllm对一些模型支持还不成熟，暂时默认关闭 # fschat=0.2.33的代码有bug, 如需使用，源码修改fastchat.server.vllm_worker， # 将103行中sampling_params = SamplingParams的参数stop=list(stop)修改为stop= [i for i in stop if i!=""] infer_turbo: False # model_worker多卡加载需要配置的参数 # "gpus": None, # 使用的GPU，以str的格式指定，如"0,1"，如失效请使用CUDA_VISIBLE_DEVICES="0,1"等形式指定 # "num_gpus": 1, # 使用GPU的数量 # "max_gpu_memory": "20GiB", # 每个GPU占用的最大显存 # 以下为model_worker非常用参数，可根据需要配置 # "load_8bit": False, # 开启8bit量化 # "cpu_offloading": None, # "gptq_ckpt": None, # "gptq_wbits": 16, # "gptq_groupsize": -1, # "gptq_act_order": False, # "awq_ckpt": None, # "awq_wbits": 16, # "awq_groupsize": -1, # "model_names": LLM_MODELS, # "conv_template": None, # "limit_worker_concurrency": 5, # "stream_interval": 2, # "no_register": False, # "embed_in_truncate": False, # 以下为vllm_worker配置参数,注意使用vllm必须有gpu，仅在Linux测试通过 # tokenizer = model_path # 如果tokenizer与model_path不一致在此处添加 # 'tokenizer_mode':'auto', # 'trust_remote_code':True, # 'download_dir':None, # 'load_format':'auto', # 'dtype':'auto', # 'seed':0, # 'worker_use_ray':False, # 'pipeline_parallel_size':1, # 'tensor_parallel_size':1, # 'block_size':16, # 'swap_space':4 , # GiB # 'gpu_memory_utilization':0.90, # 'max_num_batched_tokens':2560, # 'max_num_seqs':256, # 'disable_log_stats':False, # 'conv_template':None, # 'limit_worker_concurrency':5, # 'no_register':False, # 'num_gpus': 1 # 'engine_use_ray': False, # 'disable_log_requests': False - Qwen-1_8B: host: "127.0.0.1" port: 20008 - chatglm3-6b: # 使用default中的IP和端口 device": "cuda" # 以下配置可以不用修改，在model_config中设置启动的模型 - zhipu-api: port: 21001 - minimax-api: port: 21002 - xinghuo-api: port: 21003 - qianfan-api: port: 21004 - fangzhou-api: port: 21005 - qwen-api: port: 21006 - baichuan-api: port: 21007 - azure-api: port: 21008 - tiangong-api: port: 21009 online_llm_model: # 线上模型。请在server_config中为每个在线API设置不同的端口 - "openai-api": "model_name": "gpt-3.5-turbo" "api_base_url": "https://api.openai.com/v1" "api_key": "" "openai_proxy": "" # 具体注册及api key获取请前往 http://open.bigmodel.cn - "zhipu-api": "api_key": "" "version": "chatglm_turbo" # 可选包括 "chatglm_turbo" "provider": "ChatGLMWorker" # 具体注册及api key获取请前往 https://api.minimax.chat/ - "minimax-api": "group_id": "" "api_key": "" "is_pro": False "provider": "MiniMaxWorker" # 具体注册及api key获取请前往 https://xinghuo.xfyun.cn/ - "xinghuo-api": "APPID": "" "APISecret": "" "api_key": "" "version": "v1.5" # 你使用的讯飞星火大模型版本，可选包括 "v3.0", "v1.5", "v2.0" "provider": "XingHuoWorker" # 百度千帆 API，申请方式请参考 https://cloud.baidu.com/doc/WENXINWORKSHOP/s/4lilb2lpf - "qianfan-api": "version": "ERNIE-Bot" # 注意大小写。当前支持 "ERNIE-Bot" 或 "ERNIE-Bot-turbo"， 更多的见官方文档。 "version_url": "" # 也可以不填写version，直接填写在千帆申请模型发布的API地址 "api_key": "" "secret_key": "" "provider": "QianFanWorker" # 火山方舟 API，文档参考 https://www.volcengine.com/docs/82379 - "fangzhou-api": "version": "chatglm-6b-model" # 当前支持 "chatglm-6b-model"， 更多的见文档模型支持列表中方舟部分。 "version_url": "" # 可以不填写version，直接填写在方舟申请模型发布的API地址 "api_key": "" "secret_key": "" "provider": "FangZhouWorker" # 阿里云通义千问 API，文档参考 https://help.aliyun.com/zh/dashscope/developer-reference/api-details - "qwen-api": "version": "qwen-turbo" # 可选包括 "qwen-turbo", "qwen-plus" "api_key": "" # 请在阿里云控制台模型服务灵积API-KEY管理页面创建 "provider": "QwenWorker" # 百川 API，申请方式请参考 https://www.baichuan-ai.com/home#api-enter - "baichuan-api": "version": "Baichuan2-53B" # 当前支持 "Baichuan2-53B"， 见官方文档。 "api_key": "" "secret_key": "" "provider": "BaiChuanWorker" # Azure API - "azure-api": "deployment_name": "" # 部署容器的名字 "resource_name": "" # https://{resource_name}.openai.azure.com/openai/ 填写resource_name的部分，其他部分不要填写 "api_version": "" # API的版本，不是模型版本 "api_key": "" "provider": "AzureWorker" # 昆仑万维天工 API https://model-platform.tiangong.cn/ - "tiangong-api": "version": "SkyChat-MegaVerse" "api_key": "" "secret_key": "" "provider": "TianGongWorker" "llm_model": # 以下部分模型并未完全测试，仅根据fastchat和vllm模型的模型列表推定支持 "chatglm2-6b": "THUDM/chatglm2-6b" "chatglm2-6b-32k": "THUDM/chatglm2-6b-32k" "chatglm3-6b": "THUDM/chatglm3-6b" "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k" "chatglm3-6b-base": "THUDM/chatglm3-6b-base" "Qwen-1_8B": "/media/checkpoint/Qwen-1_8B" "Qwen-1_8B-Chat": "/media/checkpoint/Qwen-1_8B-Chat" "Qwen-1_8B-Chat-Int8": "Qwen/Qwen-1_8B-Chat-Int8" "Qwen-1_8B-Chat-Int4": "Qwen/Qwen-1_8B-Chat-Int4" "Qwen-7B": "Qwen/Qwen-7B" "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat" "Qwen-14B": "Qwen/Qwen-14B" "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat" "Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8" # 在新版的transformers下需要手动修改模型的config.json文件，在quantization_config字典中 # 增加`disable_exllama:true` 字段才能启动qwen的量化模型 "Qwen-14B-Chat-Int4": "Qwen/Qwen-14B-Chat-Int4" "Qwen-72B": "Qwen/Qwen-72B" "Qwen-72B-Chat": "Qwen/Qwen-72B-Chat" "Qwen-72B-Chat-Int8": "Qwen/Qwen-72B-Chat-Int8" "Qwen-72B-Chat-Int4": "Qwen/Qwen-72B-Chat-Int4" "baichuan2-13b": "baichuan-inc/Baichuan2-13B-Chat" "baichuan2-7b": "baichuan-inc/Baichuan2-7B-Chat" "baichuan-7b": "baichuan-inc/Baichuan-7B" "baichuan-13b": "baichuan-inc/Baichuan-13B" "baichuan-13b-chat": "baichuan-inc/Baichuan-13B-Chat" "aquila-7b": "BAAI/Aquila-7B" "aquilachat-7b": "BAAI/AquilaChat-7B" "internlm-7b": "internlm/internlm-7b" "internlm-chat-7b": "internlm/internlm-chat-7b" "falcon-7b": "tiiuae/falcon-7b" "falcon-40b": "tiiuae/falcon-40b" "falcon-rw-7b": "tiiuae/falcon-rw-7b" "gpt2": "gpt2" "gpt2-xl": "gpt2-xl" "gpt-j-6b": "EleutherAI/gpt-j-6b" "gpt4all-j": "nomic-ai/gpt4all-j" "gpt-neox-20b": "EleutherAI/gpt-neox-20b" "pythia-12b": "EleutherAI/pythia-12b" "oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5" "dolly-v2-12b": "databricks/dolly-v2-12b" "stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b" "Llama-2-13b-hf": "meta-llama/Llama-2-13b-hf" "Llama-2-70b-hf": "meta-llama/Llama-2-70b-hf" "open_llama_13b": "openlm-research/open_llama_13b" "vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3" "koala": "young-geng/koala" "mpt-7b": "mosaicml/mpt-7b" "mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter" "mpt-30b": "mosaicml/mpt-30b" "opt-66b": "facebook/opt-66b" "opt-iml-max-30b": "facebook/opt-iml-max-30b" "agentlm-7b": "THUDM/agentlm-7b" "agentlm-13b": "THUDM/agentlm-13b" "agentlm-70b": "THUDM/agentlm-70b" "Yi-34B-Chat": "https://huggingface.co/01-ai/Yi-34B-Chat" vllm_model_dict: "aquila-7b": "BAAI/Aquila-7B" "aquilachat-7b": "BAAI/AquilaChat-7B" "baichuan-7b": "baichuan-inc/Baichuan-7B" "baichuan-13b": "baichuan-inc/Baichuan-13B" "baichuan-13b-chat": "baichuan-inc/Baichuan-13B-Chat" "chatglm2-6b": "THUDM/chatglm2-6b" "chatglm2-6b-32k": "THUDM/chatglm2-6b-32k" "chatglm3-6b": "THUDM/chatglm3-6b" "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k" "BlueLM-7B-Chat": "vivo-ai/BlueLM-7B-Chat" "BlueLM-7B-Chat-32k": "vivo-ai/BlueLM-7B-Chat-32k" # 注意：bloom系列的tokenizer与model是分离的，因此虽然vllm支持，但与fschat框架不兼容 # "bloom": "bigscience/bloom", # "bloomz": "bigscience/bloomz", # "bloomz-560m": "bigscience/bloomz-560m", # "bloomz-7b1": "bigscience/bloomz-7b1", # "bloomz-1b7": "bigscience/bloomz-1b7", "internlm-7b": "internlm/internlm-7b" "internlm-chat-7b": "internlm/internlm-chat-7b" "falcon-7b": "tiiuae/falcon-7b" "falcon-40b": "tiiuae/falcon-40b" "falcon-rw-7b": "tiiuae/falcon-rw-7b" "gpt2": "gpt2" "gpt2-xl": "gpt2-xl" "gpt-j-6b": "EleutherAI/gpt-j-6b" "gpt4all-j": "nomic-ai/gpt4all-j" "gpt-neox-20b": "EleutherAI/gpt-neox-20b" "pythia-12b": "EleutherAI/pythia-12b" "oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5" "dolly-v2-12b": "databricks/dolly-v2-12b" "stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b" "Llama-2-13b-hf": "meta-llama/Llama-2-13b-hf" "Llama-2-70b-hf": "meta-llama/Llama-2-70b-hf" "open_llama_13b": "openlm-research/open_llama_13b" "vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3" "koala": "young-geng/koala" "mpt-7b": "mosaicml/mpt-7b" "mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter" "mpt-30b": "mosaicml/mpt-30b" "opt-66b": "facebook/opt-66b" "opt-iml-max-30b": "facebook/opt-iml-max-30b" "Qwen-1_8B": "Qwen/Qwen-1_8B" "Qwen-1_8B-Chat": "Qwen/Qwen-1_8B-Chat" "Qwen-1_8B-Chat-Int8": "Qwen/Qwen-1_8B-Chat-Int8" "Qwen-1_8B-Chat-Int4": "Qwen/Qwen-1_8B-Chat-Int4" "Qwen-7B": "Qwen/Qwen-7B" "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat" "Qwen-14B": "Qwen/Qwen-14B" "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat" "Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8" "Qwen-14B-Chat-Int4": "Qwen/Qwen-14B-Chat-Int4" "Qwen-72B": "Qwen/Qwen-72B" "Qwen-72B-Chat": "Qwen/Qwen-72B-Chat" "Qwen-72B-Chat-Int8": "Qwen/Qwen-72B-Chat-Int8" "Qwen-72B-Chat-Int4": "Qwen/Qwen-72B-Chat-Int4" "agentlm-7b": "THUDM/agentlm-7b" "agentlm-13b": "THUDM/agentlm-13b" "agentlm-70b": "THUDM/agentlm-70b"