From f9a5ae99eeac5e00b81abb4d371124d5b98797b6 Mon Sep 17 00:00:00 2001 From: zR <2448370773@qq.com> Date: Wed, 24 Jan 2024 15:28:34 +0800 Subject: [PATCH 1/2] =?UTF-8?q?=E6=9B=B4=E6=96=B0=E4=BA=86=E9=83=A8?= =?UTF-8?q?=E5=88=86=E4=BE=9D=E8=B5=96?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- requirements.txt | 7 ++++--- requirements_api.txt | 5 +++-- requirements_lite.txt | 3 +-- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/requirements.txt b/requirements.txt index 887d67cc..adf32a76 100644 --- a/requirements.txt +++ b/requirements.txt @@ -38,7 +38,7 @@ transformers_stream_generator==0.0.4 vllm==0.2.7; sys_platform == "linux" llama-index==0.9.35 -# jq==1.6.0 +#jq==1.6.0 # beautifulsoup4==4.12.2 # pysrt==1.1.2 # dashscope==1.13.6 # qwen @@ -47,8 +47,9 @@ llama-index==0.9.35 # pymilvus==2.3.4 # psycopg2==2.9.9 # pgvector==0.2.4 -# flash-attn==2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat -# rapidocr_paddle[gpu]==1.3.0.post5 # gpu accelleration for ocr of pdf and image files +#flash-attn==2.4.2 # For Orion-14B-Chat and Qwen-14B-Chat +#autoawq==0.1.8 # For Int4 +#rapidocr_paddle[gpu]==1.3.11 # gpu accelleration for ocr of pdf and image files arxiv==2.1.0 youtube-search==2.1.2 diff --git a/requirements_api.txt b/requirements_api.txt index e726271a..4d2ef018 100644 --- a/requirements_api.txt +++ b/requirements_api.txt @@ -52,5 +52,6 @@ llama-index==0.9.35 # pymilvus>=2.3.4 # psycopg2==2.9.9 # pgvector>=0.2.4 -# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat -# rapidocr_paddle[gpu]>=1.3.0.post5 \ No newline at end of file +#flash-attn==2.4.2 # For Orion-14B-Chat and Qwen-14B-Chat +#autoawq==0.1.8 # For Int4 +#rapidocr_paddle[gpu]==1.3.11 # gpu accelleration for ocr of pdf and image files \ No newline at end of file diff --git a/requirements_lite.txt b/requirements_lite.txt index 408033d4..6019cefb 100644 --- a/requirements_lite.txt +++ b/requirements_lite.txt @@ -30,5 +30,4 @@ watchdog~=3.0.0 # volcengine>=1.0.119 # pymilvus>=2.3.4 # psycopg2==2.9.9 -# pgvector>=0.2.4 -# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat \ No newline at end of file +# pgvector>=0.2.4 \ No newline at end of file From 852ca5f849763c50ca58bac7f07e0c6cd70431ef Mon Sep 17 00:00:00 2001 From: zR <2448370773@qq.com> Date: Wed, 24 Jan 2024 15:57:04 +0800 Subject: [PATCH 2/2] =?UTF-8?q?=E6=9B=B4=E6=96=B0=E4=B8=A4=E8=A1=8C?= =?UTF-8?q?=E6=B3=A8=E9=87=8A?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- configs/server_config.py.example | 2 -- webui_pages/dialogue/dialogue.py | 4 ++-- webui_pages/utils.py | 3 --- 3 files changed, 2 insertions(+), 7 deletions(-) diff --git a/configs/server_config.py.example b/configs/server_config.py.example index 09b1546b..eea9c34d 100644 --- a/configs/server_config.py.example +++ b/configs/server_config.py.example @@ -40,8 +40,6 @@ FSCHAT_MODEL_WORKERS = { "device": LLM_DEVICE, # 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 diff --git a/webui_pages/dialogue/dialogue.py b/webui_pages/dialogue/dialogue.py index 9efbe1d4..bf4a6e69 100644 --- a/webui_pages/dialogue/dialogue.py +++ b/webui_pages/dialogue/dialogue.py @@ -164,11 +164,11 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False): available_models = [] config_models = api.list_config_models() if not is_lite: - for k, v in config_models.get("local", {}).items(): # 列出配置了有效本地路径的模型 + for k, v in config_models.get("local", {}).items(): if (v.get("model_path_exists") and k not in running_models): available_models.append(k) - for k, v in config_models.get("online", {}).items(): # 列出ONLINE_MODELS中可直接访问且在LLM_MODELS中配置的模型 + for k, v in config_models.get("online", {}).items(): if not v.get("provider") and k not in running_models and k in LLM_MODELS: available_models.append(k) llm_models = running_models + available_models diff --git a/webui_pages/utils.py b/webui_pages/utils.py index 5a73e628..818748d6 100644 --- a/webui_pages/utils.py +++ b/webui_pages/utils.py @@ -437,9 +437,6 @@ class ApiRequest: "prompt_name": prompt_name, } - # print(f"received input message:") - # pprint(data) - response = self.post( "/chat/file_chat", json=data,